CLM-8B: Dual-Encoder Scoring and Agentic Trajectory Verification

Introduction

Recent studies in artificial intelligence are making more use of the technique of contrastive representation learning that enables the joining of contextual situational knowledge and subsequent operational activities. The direct linking of states and actions into a continuous vector space is made possible by Contrastive Language Models. The latter provides an overall approach for the evaluation of alternatives through semantic matching of decisions in continuous vectors. This enables the operational processes to be significantly faster when running, especially while implementing difficult tasks such as programming or gaming simulation. In addition, with clean scalability of vector alignment relative to data and computing power, the increase in computing and data resources leads to higher precision in the system.

For those seeking a flexible open-weights approach to contrastive learning, CLM-8B represents the ideal baseline model for modern decision-making. This model offers practical ways of implementing the evaluation of candidates and their trajectory using contrastive projections on a well-established foundation model. Using CLM-8B helps to create a flexible architecture that does away with proprietary operational dependencies in the process of deployment.

What is CLM-8B?

CLM-8B is a joint effort between the researchers from Stanford University and NVIDIA Research. This is an 8B parameter contrastive language model that serves as an open-weights 'System One' decision engine. Whereas traditional generative language models use auto-regressive token sequence prediction, CLM-8B is capable of evaluating and ranking actions based on the cosine similarity of their 512-dimensional vector representations relative to incoming environmental state.

Key Features of CLM-8B

• Independent Action Vector Caching: Precomputes and caches embeddings of potential actions  to GPU directly, needing only one pass over newly arriving environmental states.
• Zero-Token Cost for Cached Vectors: Metering  strictly counts only encoder tokens consumed by missing vectors in cache, therefore using cached vectors of actions or states takes zero encoder tokens.
• Wire-Format TypeSafe Primitive Availability: Ensures complete wire-format availability for decision-making primitives such as Noul for probability calibrated Boolean decisions, Choice for criterion multi-option decisions, and Score for rubric scoring, thus enabling direct replay of TypeSafe/Jev requests.
• Candidate Reranking Primitive: Provides a native endpoint and API-method  for evaluating and ranking arbitrary candidate text lists in one pass.
• Robotics Extension (CoVer-VLA): Applies the contrastive state-action verification concept to the robotics setting where VLA models can validate their physical trajectory via the CoVer-VLA framework.
• Prose Plain Language State Representation: Encodes state information as prose text (key: value for dictionary and -item lists for arrays) instead of encoding states as a string of JSON which skips completely parsing and schema matching issues.

Use Cases of CLM-8B

• Cost-Free Memory Management for Repeated Environment Navigation: Autonomous systems regularly navigate consistent digital environments, admin portals, or standard operational processes. CLM-8B maintains memory management cost efficiency by storing the representations of previous decisions of a model. This removes the need to incur the recurrent token cost calculation when navigating a known UI state, while keeping a steady VRAM memory footprint that ensures stability of servers during a long-running process.
• Low-Cost Adaptation for Proprietary Enterprise Taxonomies: Enterprises often have the need for an automated decision model that is aligned with their internal processes, special product catalogs or proprietary taxonomies of operation. CLM-8B supports such low-cost adaption in enterprise specific datasets with only updates to their lightweight projection heads of 20 million parameters.
• Scalable Action Routing for Large Candidate Spaces: The digital workflows of agents can often have hundreds or thousands of candidate tools as options, such as extensive microservice collections or databases in e-commerce. CLM-8B scales well in dealing with large candidate spaces by separating state evaluation from candidate embedding. This allows enterprises to scale their capability of integrating new tools without facing latency issues or cost explosion.

How Does CLM-8B Work?

The architecture of CLM-8B utilizes the concept of a dual-encoder which is constructed based on a frozen language model backbone. Instead of training the model of eight billion parameters from scratch or doing fine-tuning of the whole set of parameters, the system utilizes a frozen Qwen3-8B base encoder which extracts the hidden states representations of the input text. Two lightweight encoders with 20 million parameters—each dedicated for either environmental states or candidate actions—are used with the frozen base model. The projection heads convert the high-dimensional output from the base encoder into normalized continuous vector embeddings. While inferring, the system computes the similarity between the state embedding and each candidate action embedding. Then the system computes the scaled relative probability distribution over these similarity scores to get the ranking of the optimal action choice without generating text token-by-token.

source - |https://contrastive-lm.notion.site

This strong verification capability is achieved through a three-step alignment training process. At the initial stage of pre-training, the projection heads are trained on about sixty million question-answer pairs in order to lay down a well-defined decision space. At the second stage of mid-training, about thirty million artificial hard negatives are added to make the system more discriminative among similar and plausible choices. At the third and final stage of post-training, the system is trained on one million complex execution paths of agents. In order not to forget earlier learned concepts, this stage includes mixing of new trajectory data with replayed earlier trajectory data.

Performance Evaluation with Other Models

When considered as a trajectory verifier for multi-step agentic coding tasks, fine-tuned CLM-8B sets new records in comparison with other decision engines. On the DeepSWE benchmark, the fine-tuned CLM-8B showed 81.6% verification accuracy over 38 held-out tasks when choosing the best-of-N solution candidates produced by frontier models such as Opus 5. At the same time, proprietary joint-evaluation architectures like TypeSafe's Jev did not work as verifiers on this benchmark as their performance was worse than the random selection Pass@1 baseline.

source - |https://contrastive-lm.notion.site/

On the Terminal-Bench 2.1 benchmark, the fine-tuned CLM-8B showed 87.6% accuracy over 30 held-out tasks when verifying multi-step shell execution traces produced by Fable 5. Importantly, CLM-8B provided these verification decisions 4.1× to 5.7× faster than joint autoregressive forward passes on NVIDIA H100 GPUs. This proves that the decoupled contrastive scoring is efficient.

For short-horizon tasks such as browser games  and game scenarios, CLM-8B is on par with Jevs in terms of decision correctness with up to 9× lower average latency. With candidate spaces growing to around 1,000 actions, CLM-8B shows a 13× speed-up compared to uncached joint model evaluation thanks to the caching action vectors capability. Task-specific fine-tuning provides state-of-the-art verifiers for long-horizon executions.

How to Access And Use CLM-8B

CLM-8B is hosted on the GitHub platform in the repository named Contrastive-LM/CLM where the model parameters can be found on Hugging Face and documentation on the Contrastive-LM Notion webpage. The model can be self-hosted locally by pairing it with a local embedding server, which involves a local web playground along with the Python SDK. The CLM projection head checkpoints along with the Qwen3-8B base encoder are released as per the open-source Apache 2.0 license and can thus be used freely for any commercial purpose.

Limitations

The CLM-8B model has a number of significant limitations. First, the architecture is encoder-locked because the twenty-million parameter projection heads used by CLM-8B rely only on last-token-pooled embeddings generated by the Qwen3-8B base model and cannot be used with other backbones. Second, the model does not generate freeform text, relying solely on scoring and ranking provided candidate options. Finally, the ability of the model to generalize in zero-shot open-domain mode is limited by the eight billion parameter count. The future work will consist of developing CLM-35B in the multimodal domain.

Conclusion

CLM-8B represents a design shift in developing agents' infrastructure, which is changing the token-by-token generative evaluation for continuous vector-space contrastive alignment of the System One. The developers of scalable agentic infrastructure can use CLM-8B as a low-overhead, weights-open architecture, allowing the decision routing to be computationally and monetarily feasible.

Sources:
|https://contrastive-lm.notion.site/
https://github.com/Contrastive-LM/CLM
https://huggingface.co/Contrastive-LM/CLM-v0.1-8B

Disclaimer - This article is intended purely for informational purposes. It is not sponsored or endorsed by any company or organization, nor does it serve as an advertisement or promotion for any product or service. All information presented is based on publicly available resources and is subject to change. Readers are encouraged to conduct their own research and due diligence.

Why MiMo-V2.6 Pro Defeats Claude Fable 5 In DeepSWE v1.1

Introduction

Open-weights artificial intelligence is now at a crossroads where getting more intelligence for money determines the feasibility of production. The development of native omnimodal architectures together with scalable reinforcement learning is a recipe for establishing a transparent environment for model improvement. Making a foundation model work as an engine of both creation and analysis makes it possible for modern systems to merge textual reasoning with spatial, musical, visual, and code execution. What is essential about such models is that using groupwise agentic grading gives a way to get sophisticated reward signals, which help models to tune their complicated tool-using strategies without getting stuck in binary reward schemes. Alongside with using special optimization algorithms to guarantee training stability, open-weights models deliver frontier execution for much lower costs than those of proprietary APIs.

MiMo-V2.6 is one of the milestones in this direction – it occupies the top of world leaderboards among open-source projects and also has affordable API prices. This technology presents a single unified baseline that combines post-training reinforcement learning, open environment verifiers, and native multimodal perception.

What is MiMo-V2.6?

MiMo-V2.6 refers to an omni-native sparse mixture-of-experts (MoE) foundation model family that is purposefully designed to advance the frontier of intelligence based on inference and training costs. The model can process text, high-res images, videos, and raw audio inside a single context window of 1M tokens. MiMo-V2.6 uses reinforcement learning with large compute on multiple domains in agent-based environments to perform end-to-end tasks.

Model Variants

• MiMo-V2.6-Pro / Pro-RL: The premier MoE model with 1.02T parameter count in total with 42B parameters per token with routing to 384 experts (8 experts per token). Structured with 70 layers (one dense layer initially and 69 MoE blocks) and hidden dimension of 6,144, it has been designed for deep reasoning and long-horizon software engineering. It can be downloaded in safetensors form from a 524GB file after spending $2.62M on post-training RL compute.
• MiMo-V2.6-Flash / Flash-RL: The efficiency-balanced MoE variant featuring 309B/310B total parameters with 15 Billion active parameters per token across 256 routed experts (8 active per token). Built with 48 Transformer layers (1 dense + 47 MoE blocks) and a hidden dimension of 4,096, it delivers near-flagship agentic performance at a significantly reduced compute footprint ($0.85M RL post-training cost) and is available as a 159GB safetensors file.
• MiMo-V2.6-Distill-Qwen-9B: A compact 9B parameter dense image-text-to-text model fine-tuned from Qwen3.5-9B via Supervised Fine-Tuning (SFT) on 77.4 Billion synthetic tokens (27.2B loss-bearing tokens) generated directly by MiMo-V2.6. Balanced across coding , general agents, visual coding, and cybersecurity, it brings high-efficiency agentic capabilities to resource-constrained edge deployments.

Use Cases of MiMo-V2.6

• Making Animated 3D Scenes & Working with Robots: It can convert any type of written text, photo, or video into a 3D object, something functional in Blender. This is achieved by simplifying complex modeling and programming processes associated with robotics and gives one a real-time feedback on things happening to robots in 3D.
• Music Composition, UI Design & Multimedia Editing: It performs music composition and produces MIDI files people can work with on DAWs, produces UI design screens via Figma, and voice recordings. All of this make the creative work easier and gives independent creators a chance to compete with major companies by taking control of their audio-visual content.
• Materials development and theoretical proofs validation: Reads complex patents and literature and configures its computer programs in order to search applications of materials in the green industry while acting with active agents and generating codes for formal proofs of mathematical theorems—this enables minimizing costs of laboratory testing and patent-approving processes for scientific researchers and obtaining a pulpit for formal proofs generator.
• High Throughput Production Hosting Using Block Diffusion Speculation: Makes use of the block diffusion speculative decode along with the optimization of the inference engine in order to considerably increase the speed of the production of the output without compromising on accuracy.
• Agentic Backbone Distillation for Scalable Enterprise Swarm Deployment: Derives the lightweight agentic backbone from multimodal agentic trajectories in software engineering, general agents, visual design, and cybersecurity and enhances it with domain-specific reinforcement learning, enabling enterprises to deploy very accurate autonomous agent swarms at extremely low cost.

How does MiMo-V2.6 Work?

MiMo-V2.6 uses a hybrid sparse MoE backbone, unique omnimodal encoders, and a multi-stage training pipeline specifically for reinforcement learning scale that does not destabilize model representations. The backbone consists of alternating Local Sliding Window Attention (SWA) with Global Attention (GA). To ensure stable early representation learning, the first block of Transformers is designed with global attention using a dense Feed-Forward Network (FFN), while all other blocks use sparse MoE FFN without sharing any experts. Local SWA shrinks Key-Value (KV) cache memory overhead by 6× to 7×, while attention sink biases are learnable to ensure long-context coherence up to 1M tokens.

source- https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL/resolve/main/MiMo_V2_6_technical_report.pdf

Visual and audio signals are analyzed using specialized encoding streams. Vision utilizes MiMo-ViT, which is a 681M parameters' Vision Transformer with alternating row-major and column-major SWA tokenization along with spatial 2x2 merge. Audio analysis consists of two stages: AudioTokenizer (308M parameters), which includes 20 RVQ codebooks at 25Hz, and Audio Patch Encoder (127M parameters), which includes grouping every four frames to decrease token frequency to 6.25Hz. Mid-training context length has been increased from 32K → 256K → 1M. For weight optimization, AdamW method is being replaced by Muown (variant of Muon method with row-norm optimization) to ensure high data efficiency and avoid spectral norm drift and loss spikes during large batch training.

source- https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL/resolve/main/MiMo_V2_6_technical_report.pdf

The post-training procedure utilizes 'You Only RL Once' methodology by employing an asynchronous Group Relative Policy Optimization (GRPO) process on a batch of various tasks (coding, general agents, visual design, cybersecurity, context following) of size G=16 (25,000 rollouts per step). It is important to note that MoE routers remain frozen during the process of RL training. This ensures that there is no issue with router drift or expert-load collapse, which used to increase coefficient of variation from 0.78 to 2.0 and maximum expert load from 6x to 16x. The efficiency of post-RL training is improved via Multi-Prefix Multi-Teacher On-Policy Distillation (MOPD^2) using autonomous student rollouts along with prefix-conditioned single-turn rollouts. The Sample Mixer architecture manages extreme execution variances (up to 90× token length and 66× duration variance) through Adaptive Scheduling and Predictive Dispatch.

Performance Evaluation with Other Models

On the Artificial Analysis Intelligence Index v4.3, the performance score of MiMo-V2.6-Pro comes out to be 46.32, marking it as the best-performing open-source foundation model in the world. This model beats open-weights contenders like Kimi K3 and Qwen3.8 Max, and keeps up well with the top-performing proprietary frontier models like Claude Opus 5 and GPT-5.6 Sol. The main importance of the performance is in the intelligence-to-cost ratio because the model performs at the top level and offers the same cheap API cost as V2.5 generation.

source - https://mimo.xiaomi.com/mimo-v2-6

On the DeepSWE v1.1 benchmark for long-horizon software engineering agents shown in Table below, MiMo-V2.6-Pro scores 71.9, whereas MiMo-V2.6-Flash scores 67.9. This shows a massive rise of 52.9 points from the previous generation MiMo-V2.5-Pro. In this case, MiMo-V2.6-Pro beats Claude Fable 5 and stands on par with top-performing proprietary models like Claude Opus 5, GPT-5.6 Sol, and DeepSeek V4.1 Flash. The main importance of the performance is that scaling agentic reinforcement learning compute directly results in better repository-level debugging and autonomous multi-file editing.

source- https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL/resolve/main/MiMo_V2_6_technical_report.pdf

In terms of general agential workflow processes, MiMo-V2.6 excels in SaaS API orchestration through AutomationBench v1.0.6 and performs best in command line problem-solving through Terminal Bench 2.1, Model Context Protocol integration on Toolathlon-Verified, and economic wealth generation through GDPVal 2.1 among the open-weights benchmarks. In specific task fields, the model family achieves outstanding results in cybersecurity vulnerability replication through CyberGym and front-end visual coding through MiMo VisualCoding. Although there is a notable lag in performance in the field of competitive programming through ProgramBench and offensive exploit creation through ExploitGym, MiMo-V2.6 demonstrates the effectiveness of multi-task reinforcement learning in transferring tool-use skills into different agent environments.

How to access and use MiMo-V2.6?

Model weights, training logs and codebase of MiMo-V2.6 are completely open-sourced with MIT license. Developers and researchers can have access to the model checkpoints through the Hugging Face and ModelScope repositories . Models can be served using popular inference engines like vLLM or SGLang in an offline environment. For local run, hardware specifications depend on variant. Live telemetry, technical documentations and web demos can be found at the official website from Xiaomi.     

Limitations

The technical report documents several real-world infrastructure failure modes encountered during 1,000+ GPU RL training runs. These include hardware-level GPU memory double-bit errors (DBE), grader network unreachability, partial-rollout memory pool exhaustion, and expert-parallel activation Out-Of-Memory (OOM) spikes caused by up to 30x load imbalances across ranks prior to freezing routers. Host CPU OOM bottlenecks during trajectory packing also presented challenges.

Potential Architectural Advancements & Future Directions

In the pursuit of further advancing on the concept of omnimodal reinforcement learning, could future developments in this model include an entropy-aware, adaptively-controlled process for unfreezing routers post-freezing in the learning process? Through the combination of the localization of gradient values and dynamic expert load balancing, it is possible to incorporate this strategy, which would allow for the late adaptation of routers without the problems associated with experts load collapsing and activation memory spiking in large rollout clusters.

Also, in order to tackle host memory constraints in the trajectory packing process, could the adoption of a zero-copy, GPU-based memory pool in the sample dispatching pipeline be achieved, thus enabling continuous streamlining of multimodal rollouts? Lastly, could it be possible to unify visual and audio encoding processes in one cross-modal latent space?

Conclusion

From MiMo-V2.6, one can see that increasing reinforcement learning compute post-training across different verifier backed environments helps to get model capability improvements faster compared to increasing data pre-training. MiMo-V2.6 shows that it is capable of achieving frontier-level execution of tasks in software engineering, 3D creations, and tool orchestration. Xiaomi is an auditable foundation for autonomous agents.

Sources
https://mimo.xiaomi.com/mimo-v2-6
https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL/resolve/main/MiMo_V2_6_technical_report.pdf
https://huggingface.co/collections/XiaomiMiMo/mimo-v26
https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL
https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B

Disclaimer - This article is intended purely for informational purposes. It is not sponsored or endorsed by any company or organization, nor does it serve as an advertisement or promotion for any product or service. All information presented is based on publicly available resources and is subject to change. Readers are encouraged to conduct their own research and due diligence.

Jev: System One Decision Engine Delivering 193.6x Faster Execution

 

Introduction

In modern software engineering, there is a need to reconcile two very different paradigms – the deterministic predictability of compiled programs and the probabilistic nature of machine intelligence. Traditionally, implementing machine learning into a product entailed compromising heavily – wrapping the nondeterministic text streams into validation routines, dealing with the schema hallucinations, and suffering significant latency penalties. Reliable and deterministic output capable of being used by software directly thus became one of the key architectural challenges. In addition, it is necessary to have an architecture providing reliable software integration and full control of the logic, which means being able to avoid parsing errors at runtime and not break the program flow due to an invalid payload.

Implementing the decision-making models into the enterprise-scale infrastructure requires an architecture providing massive scalability in the production setting, while also becoming much faster and cheaper than multi-billion parameter autoregressive models traditionally used as baselines. Jev, an implementation of a special class of System One models by TypeSafe AI, solves this systemic issue by exposing the structured probabilistic judgment to the application code. It achieves this without relying on token-by-token generation and the need to evaluate the state in just one pass.

What is Jev?

Jev is an advanced, non-autoregressive System One decision engine developed by TypeSafe AI, the company co-founded by the former OpenAI employee Diogo Almeida. The engine was specifically designed for machine-to-machine reasoning, not for human-machine communication, and is capable of taking application state in unstructured form, including plain text, execution traces, or even JSON objects along with typed queries.

Key Features of Jev

• Non-Autoregressive Forward-Pass Evaluation: Evaluates input state and structured queries in a non-autoregressive forward pass, without any token-by-token autoregressive generation to avoid latency and execution overhead.
• Parallel Hardware-Aware Sampler: Scores multiple independent questions in parallel to a single shared context window without any linear accumulation of latency.
• Absolute 100% Type Safety: Avoids string generation and attains a zero type error rate along with eliminating the need for any schema validation code, regex parsing, and run-time retries.
• Three AI Building Blocks: Intelligence is expressed in terms of only three structured query types: Choice (picking one option from a defined list of 255 options), Score (rating state on a particular numerical or ordinal rubric) and Noul (testing boolean true/false condition with a 0 to 1 probability distribution).
• Probability Output Trained Through RLCD: Trained using RLCD instead of RLHF-based preference alignment that ensures statistically calibrated probability outputs.
• Unilateral Metering Scheme: Charged in terms of input tokens rate of $0.042 per million tokens ($42/B tokens) and with output tokens being offered absolutely free of cost ($0.00).

Use Cases of Jev

• Speculative Fan-Out State Assessment: Running multiple-variable policy assessment, routing policies, and compliance policies all at once on a single payload, so the software can use all of the decision outcomes in a single atomic operation.
• Low-Latency Command Safety & Security Firewall: Acting as a synchronous, pre-execution guard that filters raw API calls and shell commands for prompt injection attacks or policy breaches before executing them downstream.
• Reflexive Physical Control in Real-Time in Physical and Simulated Worlds: Acting as a real-time decision engine for simulated worlds, game engines, and robots who need to perform reflexive actions in response to observational data.
• Verification Layer for Generative LLMs: Acting as an additional validation layer placed after traditional conversational models that check if the responses are factually correct, comply with policies and have a proper form before sending responses to the end-user.
• Confidence-Controlled Choice of Agentic Tools: Being the decision brain of agentic tools, which will allow you to make a choice using the Choice primitive and immediately escalate a low confidence decision to the fall back procedure.
• High Throughput Routing & Scoring of Tickets and Emails: Sorting, scoring the level of urgency, and routing a high volume of tickets and emails directly into the database queue with no human involvement.

How Does Jev Work?

Structurally at its core, Jev changes the interaction between foundation models and application code, substituting probabilistic evaluation for the token generation process. In order to ask a question, application passes an unstructured input in the form of a JSON object, an execution log or any other text, together with a series of questions, described in Choice, Score, or Noul primitives in the form of an array of atomic questions. Instead of passing this information to autoregressive decoders generating text letter by letter, Jev transfers the state and the list of questions to the hardware-aware parallel sampler.

source - https://docs.typesafe.ai/introduction

The way the model is executed is closely associated with its post-training alignment technique called Reinforcement Learning for Calibrated Decisions (RLCD). As opposed to standard language models trained via Reinforcement Learning from Human Feedback (RLHF), which are optimized for maximizing human preference and hence suffer from mode dropping, overconfidence and deceptive certainty around decision boundaries, RLCD aims at optimizing the probabilities of the output of the model directly against its empirical classification outcomes. Hence, Jev produces mathematically calibrated confidence scores along with every typed value.

Potential Architectural Enhancements

Could it be possible to compile Jev’s non-autoregressive, parallel sampling engine on edge-level neural processing units (NPUs) or on specialized FPGA acceleration boards? Moving this engine from the hosted environment of cloud nodes to hardware-based environments can open up the opportunity to have less than 10 milliseconds reflex loops for embedded robots, navigation fleets, and industrial IoT. Moreover, adding state differencing along with the activation cache will enable the monitoring system to analyze live data streams without re-tokenizing static backgrounds.

On the other hand, concerning post-training and research side, extension of the RLCD framework by cross-modal joint embeddings will enable direct probability-based evaluation of video streams, audio data, spatial sensors without any text transduction at all. To overcome one-pass cardinality limitations, it is possible to implement dynamic and speculative tree cascading right into the forward pass. Such modification will enable hierarchical routing of decisions across thousands of available options in one-pass manner and still guarantee type safety.

Performance Evaluation with Other Models

For measuring the efficiency of decision-making in real-world scenarios, TypeSafe AI performed the performance evaluation of other models with the help of structured compute graphs of the real-life production business logic and not through any static benchmark datasets. The baseline reference distributions have been derived based on the average results of the leading frontier models such as GPT-6 Astra and Claude Fable 5.1. In order to perform comparative tests, all the standard LLMs were evaluated using TypeSafe AI’s System One, which forced them to output only structured decisions and probabilities.

source - https://typesafe.ai/blog/introducing-system-one-models-and-jev

Jev showed an extremely radical difference when tested with the speed and latency benchmarks. Where the standard frontier LLMs needed 3 to 329 seconds to execute structured decision workflows, Jev completed the task within 70ms to 500ms. On representative production workflow benchmarks, the time required to perform decision cycles was 0.114 seconds for Jev against 8.566 seconds for the standard LLMs, which gave a 193.6x improvement. Moreover, per-workflow execution costs were reduced from $0.013880 for standard frontier models to $0.000081 for Jev, giving a cost reduction of 444.6x.

The synopsis of the benchmarks highlights a paradigm shift in production economics and reliability of systems. The fact that Jev achieves the feat of having a type error rate of 0% means it removes validation delay, regex parsing, and retries that are a constant feature of conventional LLMs. Input pricing comes down to $0.042 million tokens, which is 238x cheaper than the Claude Fable 5.1. Output tokens come free of charge, making Jev bring back the Pareto frontier for workflow intelligence to cost ratio.

How to Access and Use Jev?

The proprietary and hosted Jev API is available as early access on the TypeSafe AI platform through an onboarding waitlist. The model cannot be executed locally as there are no open-weights or self-hosted versions of the model available yet. The integration of Jev into production-ready systems can be done using the official Client SDKs that have been provided in Python and JavaScript/TypeScript or directly via REST API.

Limitations and Future Work

Despite the efficiency that Jev is able to offer in terms of speed and reduced costs, the unique architecture used in Jev has limitations of function as well. First, it does not support open-ended string creation at all making it unusable in conversational chatbots, copilots and generative code creation. Built solely for single pass System 1 classification, it cannot perform multi-step inference or analysis of multi-faceted tradeoffs in one prompt and requires developers to break down problems into smaller atomic questions within application logic. The Choice primitive supports a maximum cardinality of 255 choices – thus, requiring a slower process of scoring in two stages when dealing with greater number of choices – as well as limited input states which include only text and data.

In order to overcome these limitations, the technical road map of TypeSafe AI includes development in areas of expanding input types to cover visual and multimodal data, System One model pipeline extension, developer workshops and hackathons and onboarding from the waitlist. Future work will focus on showing computational and economic viability of its parallel sampling architecture and RLCD training.

Conclusion

Jev demonstrates that specialization of foundation models for non-autoregressive decision execution provides outstanding benefits. It even demonstrates that separation of probabilistic reasoning and text generation allows for creating a fast, affordable, and type-safe primitive that becomes a part of the deterministic codebase. For infrastructure professionals looking for the ways to automate the logic without significant latency and validation costs, Jev sets a benchmark for the future of machine-native AI infrastructure.

Sources
https://typesafe.ai/blog/introducing-system-one-models-and-jev
https://typesafe.ai/
https://docs.typesafe.ai/introduction

Disclaimer - This article is intended purely for informational purposes. It is not sponsored or endorsed by any company or organization, nor does it serve as an advertisement or promotion for any product or service. All information presented is based on publicly available resources and is subject to change. Readers are encouraged to conduct their own research and due diligence.

Nex-N2.5: Open-Weight AI That Controls Web Browsers and Desktop OS

Introduction

There is currently an enormous paradigm shift taking place in modern sparse open-weight architectures in how they process multimodal streams. Rather than treating graphical streams as passive data input or using text-based command chains only, today’s architectures such as Nex-N2.5 take advantage of optical perception streams for ongoing runtime error correction. This architectural advance provides a way of overcoming the frailties of traditional automation pipeline design, which cannot cope with minor interface rendering errors or unexpected terminal outputs during multi-turn processes.

It is important to strike a balance between selective parameter passing and efficiency when running autonomous extended processes in the enterprise environment. Being able to adapt the computing infrastructure for advanced computation to work for workflow is key to achieving efficient execution in software engineering, web navigation, and interface control. It is through making such hardware optimization work in combination with closed-loop image validation to provide self-rectification in an autonomous manner that modern architectures such as Nex-N2.5 achieve desktop agency and multi-step reasoning without dense latency cost.

What is Nex-N2.5?

Nex-N2.5 is a family of Mixture-of-Experts (MoE) models developed by Nex-AGI, explicitly purpose-built for visually grounded agency, native desktop and web GUI navigation, autonomous software development, and closed-loop execution. Transitioning from traditional text-heavy agent frameworks, the model utilizes continuous visual perception as a real-time verification interface to execute code, manage operating systems, navigate complex web applications, and self-correct system actions based on observed environmental states.

Model Variants

• Nex-N2.5-mini: Runs on 35 Billion total parameters (MoE) with 3 Billion active parameters per token (A3B). Built on top of the Qwen3.5-35B-A3B-Base multimodal foundation, this model is designed to achieve fast instruction-following, low-latency API serving, and on-the-fly tool execution. Efficiently running on a single node featuring 2×H100 GPUs with Tensor Parallelism (TP=2).
• Nex-N2.5-Pro: Equipped with 397 Billion total parameters (MoE) with 17 Billion active parameters per token (A17B) and built on top of the Qwen3.5-397B-A17B multimodal base, this is the main workhorse model for complex reasoning, multi-agent orchestration, and all-in-one developer stack. Designed for efficient running on a single node with 8×H100 GPUs (TP=8) using the dedicated NexRT inference engine.
• Nex-N2.5-Max: This is the flagship variant equipped with 1.6 Trillion total parameters (MoE) with 49 Billion active parameters per token (A49B). In contrast to other variants, this one uses the DeepSeek-V4-Pro-Base text-only foundation model for deep reasoning, scientific research modeling, and high-level architectural code generation. Efficiently running on multi-node clusters.

Key Features of Nex-N2.5

• Visually Grounded Agency & Closed Loop Self Correction: Controls web browsers and desktop operating systems through a visually grounded feedback loop. This model performs visual action execution, visual UI update evaluation, detects rendering bugs/page anomalies, and dynamically re-plans execution in real time, without any human involvement.
• Native GUI Navigation & Normalized Grounding: Can perform exact cursor-mouse actions in both desktop and web applications. For achieving spatial precision in different resolutions (OSWorld, WebArena, and WebTest benchmarks), normalized grounding is used in a standardized 0–1000 spatial grid.
• Coherent Logic & Multi-Step State Traversal: Maintains coherent reasoning capabilities across the entire process of task decomposition, strategic changes, visual state traversal, and self assessment within complex context switches.
• Trillion Parameter Scale Post Training Pipeline: Represents the first time Nex-AGI is attempting a post training process at a 1.6 trillion parameter scale. The pipeline receives live terminal output, web DOM tree, and screenshot streams directly into the training loop.
• Heterogeneous Base Foundation Models: Uses a combination approach by utilizing multimodal Qwen3.5 models with visual spatial interactions (Mini and Pro) as well as a 1.6T text only DeepSeek-V4-Pro base (Max) for logical synthesis.

Use Cases of Nex-N2.5

• Dual Model Autonomous Code Refactoring & Visual Playtesting: Facilitates automation of CI/CD pipelines where the state-of-the-art reasoning model rewrites complex codebase, and a multimodal model serves as the workhorse that builds up the software, opens the GUI, validates the UI rendering against design specifications and sends the screenshot differences to the code refactoring model to perform corrections before merging.
• Closed Loop Visual GUI Navigation with Autonomous Corrections: Navigates through browser and desktop applications checking the visual state after each click, and autonomously changes the path execution if unexpected popups appear or sites are broken.
• Multi-Backbone Models Inference under a Single Gateway: Simplifies enterprise inference management through serving of lightweight, medium, and ultra-heavy models under one standardized API gateway with custom server-side reasoning and tool-parsing routers.
• Zero-Script Legacy ERP and Desktop Workflow Automation: Automates multi-step workflows within enterprise applications including legacy ERP and desktop applications as well as mainframes emulators, using screen vision and normal coordinates control, without the use of unreliable APIs and RPA scripts.
• Engineering Task Criticality-Based SLA-Allocation of Compute Resources: Minimizes company compute cost by allocating developer traffic depending on the criticality of their tasks, sending code completion to high performance 2× H100 machines, feature requests to mid-performance 8× H100 machines and architecture-related tasks to high end multi-node machines.
• Cost Margin and Latency Management via Reasoning Control: Controls product margins and latencies by configuring API requests to skip the thinking trace, use adaptive thinking trace or deep reasoning trace depending on the criticality of the request.

How Does Nex-N2.5 Work?

Nex-N2.5 integrates an execution-feedback loop into its post-training flow, end-to-end. Instead of making predictions for the next tokens based only on pairs of instruction and response that don’t change during training, the training procedure makes the model experience the live execution environment by receiving terminal output streams, web DOM tree structures, and desktop screenshot streams in real-time. Consequently, the model learns to map raw vision observations directly to useful tool invocations and normalized keyboard/mouse coordinates on a 0-1000 spatial grid.

To enable efficient decoding in real-time on the 8xH100/H200 GPU cluster of Nex-N2.5-Pro, Nex-AGI has developed the dedicated inference engine NexRT. The engine supports Standard Decoding with Multi-Token Prediction (MTP) and DFlash block-diffusion. The engine features custom CUDA kernels, full decode CUDA Graphs, GPU Direct between nodes communication, and Context-Parallel Attention (CP) that allows avoiding duplicate KV cache reads with extended context windows.

Performance Comparison with other Models

In the context of web browsing and long context information synthesis, BrowseComp draws attention to Nex-N2.5-Max which has achieved the #1 rank worldwide and is directly better than some of the best proprietary frontier models like Claude Opus 5 and GPT-5.6 Sol. In addition to that, under the same evaluation paradigm, Pro and mini versions have shown significant generational improvements compared to their predecessors. While showing superiority in web browsing, Nex-N2.5-Pro has achieved the #1 rank worldwide in OSWorld-G spatial grounding benchmarks, beating other best visual and multimodal models like Qwen3.8-Max, GLM-5.3-Flash, GPT-5.6 Sol, and Claude Opus 5.

source - https://nex-agi.com/

When it comes to software engineering for repositories and debugging multiple files, the evaluations on SWE-Bench Pro and DeepSWE v1.1 show how well the model can generate code and solve problems. The model, compared to leading open-weight models such as DeepSeek-V4-Pro and GLM-5.3, shows better results on most of the important agentic, web, and programming benchmarks, while on other benchmarks, such as SWE-Bench Pro and GUI navigation in space, it shows competitive performance with some targeted leads. This good performance showcases the efficiency of the model suite in dealing with large full-stack codebases and autonomous engineering problems.

source - https://nex-agi.com/

In all types of agentic workflows, desktop operating system controls, and multi-turn execution of tools, Nex-N2.5 remains consistently powerful in different evaluation sets. In all evaluation sets for workflow and knowledge performance such as GDPval-AA v2, AutomationBench, and Toolathlon Verified, the Max version is superior to top frontier agents such as GPT-5.6 Sol, GLM-5.3, Kimi-K3, and DeepSeek-V4-Pro. Also, the excellent performance on Terminal-Bench, OSWorld-Verified, and OSWorld-2 shows the cross-domain versatility of the family of models, proving that the feedback loop for perception and execution in reality is successful.

How to Access and Use Nex-N2.5?

Model Weights for Nex-N2.5 are available under the Apache-2.0 License through Hugging Face and ModelScope, while the codebase is available at GitHub. Hosted API endpoints can be accessed through OpenRouter.  Reasoning efforts during API calls can be dynamically controlled through 'reasoning_effort'. During SGLang deployment, launching scripts require providing '--tool-call-parser qwen3_coder', as well as corresponding reasoning parsers: '--reasoning-parser qwen3' for Mini/Pro or '--reasoning-parser deepseek-r1' for Max.

Limitations and Future Work

Using the Nex-N2.5 framework involves significant overhead in terms of hardware infrastructure as the Max model needs at least 16× H200 GPUs in 2 nodes with DeepEP/DeepGEMM networking, whereas the Pro model needs an 8× H100 node with SGLang patches for ideal token decoding. Going forward, work will focus on using trillion-scale post-training knowledge for larger foundation backbones and complete open-source availability of the NexCUA evaluation framework.

Conclusion

Nex-N2.5 presents an implementation strategy for open weight agentic architectures in transforming computer vision into a proactive visual execution cycle instead of a passive description method. It illustrates the way in which enterprise automation systems can move away from fragile brittle scripting to visual self-correcting autonomy through the use of precise spatial grounding along with customized inference engines such as NexRT.

Sources:
https://nex-agi.com/
https://github.com/nex-agi/Nex-N2.5
https://huggingface.co/collections/nex-agi/nex-n25
https://huggingface.co/nex-agi/Nex-N2.5-Max
https://huggingface.co/nex-agi/Nex-N2.5-Pro
https://huggingface.co/nex-agi/Nex-N2.5-mini


Disclaimer - This article is intended purely for informational purposes. It is not sponsored or endorsed by any company or organization, nor does it serve as an advertisement or promotion for any product or service. All information presented is based on publicly available resources and is subject to change. Readers are encouraged to conduct their own research and due diligence.

How Claude Fable 5.1 Cuts Heavy Agent Costs by 45 Percent

Introduction

Generative models of great capacity come with a fundamental trade-off of being unshackled from reasoning power versus safety. In mission-critical engineering, telemetry, and software workflow automation, continuous reasoning in large contexts calls for a balance of great model autonomy and dynamic hazard mitigation. Instead of using static refusal of execution that leads to a stoppage of multi-turn reasoning in complex processes, modern frontier systems use classifier shielded designs. This design separates dual-purpose threats while still keeping great analysis capabilities, thus leading to fast growth in bio-computational and planetary mapping domains. Using secure access routes for accredited domain experts and run-time safety zones for deployment of the model, a framework is set in place for stable sovereign enterprise operations. Evaluation of Claude Fable 5.1 offers great insight into this balance of agential autonomy, safety, and long-horizon execution cost in modern system design.

What is Fable 5.1?

Fable 5.1 Claude is the latest state-of-the-art Claude generation model from Anthropic. It is built for advanced horizon reasoning and software engineering with a very large window of context. It is one of the Claude models that functions as a classifier-shielded system and represents the topmost point of the entire Claude generation model family. The model was designed to perform agentic operations within multi-hour long loops.

Key Features of Fable 5.1

• The prompt caching optimization: It minimizes read costs to $0.25 for each million tokens, which is a decline of 75% from the traditional costs of token usage. This results in the reduction of operational expenditures up to 25% for normal workloads, and up to 45% for contextually heavy tasks involving agents.
• Protection of Context State & Intellectual Property: Anti-distillation mechanisms are included in the system to stop any new API accounts from modifying earlier context states while using multi-turn services. Thanks to this design choice, internal processes such as thinking blocks and logical sequence of thought are safe from extraction.
• Shielding of classifiers using precise calibrations: A newly installed and redesigned system of real-time safety probes allowing for a decrease by 60% of the number of cases of cyber-guardrails in each session and a reduction of 85% of their application on harmless questions related to basic biology or medicine.
• Granular Code Analysis Guardrail Thresholds: These custom-tuned safety parameters are set up with a view to provide a method for performing automated static code analysis and source code vulnerability detection irrespective of the level of access. They help to differentiate ordinary code inspection from penetration testing or exploitation. 
• Cryptographic Output Provenance: It is essentially a statistical watermarking measure that is incorporated into a circuit design. It gives a mathematical means to establish the authorship of the work done by the models and comply with the AI Act of the EU authorities. 
• Sovereign Cloud Data Isolation (EFS): Fable is built on an infrastructure that permits the storage of interaction logs and the use of CMEK within the private cloud of Amazon S3, Google Cloud Storage, or Azure Blob. This function eliminates the need for using third-party logging services while keeping platforms cost-free. Its operation adheres to strict ZDR requirements.

Use Cases of Fable 5.1

• Zero-Trust Continuous Codebase Auditing and Vulnerability Discovery: DevSecOps and software developers are able to deploy autonomous agents overnight scanning through millions of lines of codes. The model is capable of conducting deep static  analysis and analyzing complex vendor library dependencies, finding memory leaks and zero-day vulnerabilities without causing repetitive false-positive security denials. 
• Legally Verifiable Content Generation and Regulatory Compliance: Enterprises’ compliance specialists and legal technology teams are able to generate complex regulatory submissions, corporate policies, and intellectual property disclosures. Cryptographic watermark will ensure compliance with transparency requirements in the European Union whereas EFS will make sure that the private information will be stored exclusively in sovereign clouds.
• Fail-Safe High Acuity Scientific Research and Spatial Modeling: Academic and research institutions will be able to conduct high throughput computational modeling including multi-decadal planetary radar data for topographical mapping of planets or biocomputational simulation without risks of being halted due to dual-use query classification.
• Unattended Multi-Hour Agentic Workflows & System Migrations: The infrastructure and process automation experts can run more than 30 hours unattended migrations and diagnostics. The autonomous agents from Fable 5.1 correct runtime mistakes, control the parallel execution pipelines of experiments, log the internal activity, and rebuild the old applications without losing any context and logic consistency on multiple steps.
• Parametric CAD Engineering and Multimodal Technical Operations: Using parametric CAD engineering and multi-mode technical processes, hardware engineers and CAD engineers can upload large Spatial Plans and geometric figures that can then be used for real-time optimization of tolerances, validation of parametric designs, and the resolution of various assembly problems through the one million input parameters.

How does Fable 5.1 Work?

Fable 5.1 by Claude uses a dense transformer-based reasoning model capable of processing large volumes of data within a real-time and multistage classification shielding. Upon processing any input prompt through the 1,000,000-token capacity context window, specific probes will analyze the input tokens and generated tokens on trajectory. While other models may simply shut down the request once they recognize dual-use signals in restricted areas, such as biological sequences and cyber exploitation, Claude uses Active Fallback Routing. This feature reroutes any queries with risks to specific fallback models, such as Claude Opus 4.8 for cybersecurity vectors and Claude Opus 5 for biological computational vectors.

Further system security and alignment are enabled by the use of the anti-distillation defense mechanism and Enterprise Frontier Safeguards (EFS). The anti-distillation mechanism keeps track of multi-turn API conversations and prevents accounts from changing context blocks in history in order to distill reasoning traces without changing the natural thoughts outputs. On the other hand, the EFS system makes sure that data durability is separated from model hosting and creates API streams that transfer prompt history and key management information directly to customer-owned storage buckets.

Performance Evaluation with Other Models

The benchmarking tests to evaluate the performance of Fable 5.1 in terms of long-horizon software engineering and agentic execution have demonstrated its excellent capability. In the initial evaluations of the capabilities of the system highlighted in the table below, Fable 5.1 has been very successful, scoring 81.2% in SWE-bench Pro. This is better than the previous model, Fable 5 (80.0%), as well as other models such as Claude Opus 5 (79.2%) and GPT-5.6 Sol (64.6%). The performance shows that the model has the capability to not take the shortcuts leading to lower quality work and solve the fundamental issues of software. Moreover, the early access partners reported that Fable 5.1 has executed agentic runs for 38 hours without any problem.

source - https://www-cdn.anthropic.com/0339e6a7c5c7b87f5c07798616dc32c215d14235/Claude%20Fable%205.1%20&%20Claude%20Mythos%205.1%20System%20Card.pdf

In the case of task completion and reasoning for particular science-related terminal tasks, Fable 5.1 made great progress. As can be seen from the table above, the model obtained 52.6% on Terminal-Bench-Science 0.1 benchmark, which is more than two times better compared to Fable 5 (24.7%) and beats Opus 5 (29.0%). In case of Humanity's Last Exam (HLE) Fable 5.1 managed to get 60.9% without tools and 65.0% with tools, beating Fable 5 (57.8%/63.8%) and Opus 5 (56.6%/63.6%). Furthermore, the model achieved impressive result of 73.4% accuracy on CursorBench 3.2.0 at max effort.

source - https://www-cdn.anthropic.com/0339e6a7c5c7b87f5c07798616dc32c215d14235/Claude%20Fable%205.1%20&%20Claude%20Mythos%205.1%20System%20Card.pdf

Further benchmark synthesis demonstrates the flexibility of the model for multimodal, legal, and agentic tasks. Fable 5.1 did great on benchmarks for legal agent frameworks (90.81% mean criterion-pass rate on Legal Agent Benchmark - LAB) and vision-based data synthesis (GDP.pdf at 85.4% without tools). What is especially important to highlight is the safety and security profile of the model: the attack success rate of the model was only 0.1% at k=1 on the external Indirect Prompt Injection (IPI) benchmark.

How to Access and Use Fable 5.1?

The Fable 5.1 variant of Claude is available as a proprietary API endpoint hosted in the cloud with the ID claude-fable-5-1 . It has native integrations with Claude Code, Claude Cowork, AWS Bedrock, Google Cloud Vertex AI, and Microsoft Azure. Due to its large scale of parameters and proprietary classifier shielded architecture; only API calls can be used to interact locally.

Limitations

Nevertheless, there are certain operational limitations to Fable 5.1 that systems engineers have to consider. First of all, when classifier probes lead to the engagement of Active Fallback Routing in automated benchmarking tests, the execution path will be redirected to fallback models, resulting in a zero-score failure in the given testing phase even though the security hazard has been dealt with successfully. Furthermore, red-team evaluations reveal that although the model demonstrates good resistance to single-turn attacks, it is vulnerable to multi-turn framing attacks, such as deep academic role-playing.

Conclusion

Claude Fable 5.1 illustrates how state-of-the-art model reasoning can coexist alongside thorough safety at a corporation without having to compromise either one. With the substitution of the coarse-grained rejection systems for the flexible classification protection, proactive fallback routing, and aggressive lowering of caching costs for prompts, Anthropic was able to develop a system that allows for reliable operation of agentic loops lasting several hours.

Sources:
https://www.anthropic.com/claude-fable-and-mythos-5-1
https://www-cdn.anthropic.com/0339e6a7c5c7b87f5c07798616dc32c215d14235/Claude%20Fable%205.1%20&%20Claude%20Mythos%205.1%20System%20Card.pdf
https://www.anthropic.com/news/enterprise-frontier-safeguards
https://www.anthropic.com/news/improving-fable-5-s-biology-safeguards


Disclaimer - This article is intended purely for informational purposes. It is not sponsored or endorsed by any company or organization, nor does it serve as an advertisement or promotion for any product or service. All information presented is based on publicly available resources and is subject to change. Readers are encouraged to conduct their own research and due diligence.

GLM-5.3-Flash: 320B Open-Source Native Multimodal Agentic Model

Introduction

There is an evolution from text-based processing into the natively-perceiving and interacting with the graphics interface. Enterprise teams working on scaling automation face significant challenges through the use of disjointed, textual-only pipelines. Building an agentic infrastructure at scale requires a totally different engine; one which incorporates screen-based programming and iterative graphical rendering tests directly in the core loop of its logic.

GLM-5.3-Flash sets a new benchmark in this regard. The use of sparse and linear structural design shows that running tasks in the autonomous manner over long horizons is not necessarily accompanied by excessive computational cost. Companies should use it since it provides cutting-edge agentic capabilities along with document processing in extremely economical terms.

What is GLM-5.3-Flash?

GLM-5.3-Flash is a 320B parameter (18B active) native multimodal foundation model created by Z.ai, designed to be an autonomous partner in production as opposed to a conversational interface. Training on 30 trillion token multimodal dataset, it can process text, code, images, as well as any file format at once, allowing it to perform multi-step professional workloads - from automated UI development to auditable financial research - using agentic frameworks.

Key Features of GLM-5.3-Flash

• Native Graphical User Interface and Interface Automation: Vision is natively integrated within the running processes and can directly interact with desktop and web applications. It uses frameworks such as vLLM, SGLang, or TokenSpeed and applies Computer Use protocols in order to convert screen recordings and designs into Next.js applications, automatically verifying their states of interaction and components.
• Spatial and Parametric Engineering Design Generation: Besides creating websites, it understands 3D spatial relations. It can create parametric CAD scripts using the build123d framework and complete 3D scenes in Blender while continuously adjusting their layouts based on the feedback about the structure.
• End-to-End Office Document Audit: The tool builds complex PDF, PPTX, DOCX, and XLSX documents and manages both information architecture and formatting at the same time. It creates the renderings in order to detect and correct possible layout issues such as text overflowing, wrong alignment of charts, etc.
• Long-Context Execution Support: It was designed for running multi-step operations and has a huge 1 million token context window. Using the efficient IndexPool algorithm, it compresses key vector caches in order to minimize memory usage and keep large projects and financial documentation open and ready for long-horizon analysis.

Use Cases of GLM-5.3-Flash

• Automatic Visual Audit for Massive Numbers of Enterprise Documents: In generating and processing massive numbers of documents on a daily basis like PDFs, PPTXs, and DOCXs, there is bound to be some issues related to poor formatting in terms of things like overlapping tables or misplaced text. This application uses an automatic quality assurance pipeline based on screenshot rendering of the documents.
• Automated Generation of Executable 3D Parametric CAD from 2D Physical Blueprint: Design engineers get an opportunity to transform detailed and technically advanced multiview physical blueprint images into executable 3D CAD script automatically. While doing so in headless environment, the process visually checks the physical boundary and mathematical tolerance against the original 2D blueprint image to accelerate the entire process manually.
• Massive Refactoring & Security Patching of Legacy Codebase: In the context of huge and monolithic code repositories which include almost a million tokens, semantic searches, security patches, or legacy API contract updates turn into cost-prohibitive operations. Using this tool, you can run huge agentic sweeps through dozens or hundreds of code repositories at off-peak hours like weekends to patch deep-rooted structure-related bugs.
• Running Hundreds of Real-Time Desktop Agents Optimized for Sovereign AI Accelerators: Enterprises required to use only domestically produced AI accelerators need extremely efficient performance for operating GUI-operating systems. It allows launching hundreds of concurrent real-time agents which perform simultaneous clicking, typing and reading of live screenshots.

How Does GLM-5.3-Flash Work?

In terms of architecture, GLM-5.3-Flash comes up with the innovative Sparse-Linear Hybrid Attention architecture, becoming the first openly available model of such scale to be built around this specific combination of structures. It operates with 320B total parameters, but activates 18B parameters per token using the advanced MoE sparsity. To focus on extremely high inference speed and low latency as its priority, the model cuts down its total depth in half, working with 45 layers instead of 92 layers in the GLM-4.5 family. Linear attention structures solely take care of the representation of local dependencies, while the sparse attention layers extract relevant global context using the highly optimized, lightweight indexer.

source - https://z.ai/blog/glm-5.3-flash

In order to tackle the critical problems of memory scaling related to large context windows, the model employs IndexPool Key Compression technique. This approach succeeds in compressing four different indexer key vectors into one by using the specific weighted pooling, which reduces KV-cache size 4.44 times and cuts attention computations 3.01 times compared to the flagship GLM-5.3. It is pre-trained on an absolutely unprecedented 30-trillion-token multimodal dataset (much larger than both GLM-5 and DeepSeek-V3) and uses Manifold-Constrained Hyper-Connections (mHC) topology to optimize its scaling behavior. As for physical deployment, it uses Encode-Prefill-Decode (EPD) disaggregated cluster architecture. Thanks to the specific ReplaySSM kernels, hybrid INT8/FP8/BF16 cache quantization, W8A8 weight-activation quantization, and layer-split memory allocation, multimodal encoding and token-by-token decoding are divided into separate worker pools.

Architectural Equivalents & Optimization Paths

Even though GLM-5.3-Flash creates a very high benchmark, an analysis of other comparable hybrid architectures, particularly Kimi K3 and NVIDIA Nemotron 3, shows that these architectures have different operational characteristics. The thing is that Kimi K3 and Nemotron 3 are based on similar design principles: delegation of local dependencies to algorithms and use of dense/sparse attention exclusively for global context retrieval. Still, GLM-5.3-Flash outshines in terms of extreme latency reduction and hardware scalability. Namely, through the use of unique IndexPool Key Compression, this model reduces the cost of supporting its 1M-token context window by pooling four keys in one, which is very helpful during long-horizon codebase sweeps. In addition, through a conscious cutback of the neural network to just 45 layers, it reaches the ultra-low latency necessary for visual interface real-time operations.

However, in turn, other architectures have some structural advantages that point towards clear optimization paths. Nemotron 3 Super uses Mamba-2 State Space Models (SSMs) which by definition have the ability to track local dependencies in a more memory-efficient way compared to linear attention of GLM-5.3-Flash. At the same time, Kimi K3 implements Attention Residuals throughout a far larger 93-layer neural network, allowing selective representation retrieval which does not allow information loss at extremely large sequence lengths. There are many opportunities for improvements in terms of implementation of GLM-5.3-Flash, and it can greatly benefit from both mentioned above techniques. Thus, Attention Residuals may perfectly compensate any logic drops due to the shallow depth of 45 layers in the architecture.

Performance Evaluation with Other Models

Starting from foundational pre-training evaluations, the 18B active parameter GLM-5.3-Flash-Base shows clear supremacy over bigger base models. Tested in table below: Pre-trained Base Model Comparison, its best benchmark score appears to be achieved on LiveCodeBench-Base, where it scores 37.6 points. This clearly outperforms the old flagship GLM-4.5-Base and gains a decisive win against the big GLM-5-Base. Significance of this evaluation proves that despite utilizing very optimized active parameter count – less than half of the parameters used in GLM-4.5-Base and GLM-5-Base – the model manages to achieve better baseline logical and coding reasoning, thus proving structural efficiency of its 30T multimodal pre-training and sparse-linear hybrid architecture.

source - https://z.ai/blog/glm-5.3-flash

During evaluation of the Chat/Instruct variant in complex coding and agentic execution environments, GLM-5.3-Flash scores its second top benchmark breakthrough on DeepSWE v1.1 (as shown in table below), scoring 63.4 points. This is a huge advance for its predecessor GLM-5.2, outperforming such closed-source flagships as Claude Opus 4.8. Moreover, it scores 1773 points on GDPval-AA v2, outperforming not only Claude Opus 4.8 but Gemini 3.7 Flash as well. This evaluation proves that the model has the ability to perform end-to-end, multi-step software engineering resolutions independently, thus proving that operational cost optimizations do not mean poor quality or instability of reasoning and execution.

source - https://z.ai/blog/glm-5.3-flash

Within the wider array of benchmarks, GLM-5.3-Flash continues to demonstrate its supremacy compared to older flagships and smaller rivals. The scores of GLM-5.3-Flash include 48.8 on AutomationBench v1.0.6, 78.4 on Toolathlon Verified, and 84.3 on Terminal Bench 2.1, which always outperforms Claude Opus 4.8 in complicated agents. With respect to multimodal vision benchmarks, GLM-5.3-Flash scores 89.4 on CharXiv Reasoning w/ Tools, 80.5 on MMVU, and 77.8 on MVbench, easily beating smaller MoE models such as DeepSeek-V4-Vision-Exp. All of the above clearly show that the model provides cutting-edge vision-language understanding and tool operation.

How to Access and Use GLM-5.3-Flash?

The engineers and system integrators will have access to its core resources straight from the official Hugging Face repository of the model. This open-source and commercial-friendly licensed model comes with weights that can either be hosted locally or scaled out using stacks like vLLM and SGLang. For execution of workflows, it runs inside agent harnesses like Claude Code and connects to the ZCode desktop client in order to control the GUI visually. Teams that prefer using APIs may make use of GLM Coding Plan with its point system for quotas.

Limitations and Future Work

Apart from being revolutionary in terms of parameter efficiency, there are some limitations to GLM-5.3-Flash’s architecture. In particular, the size of its KV-cache, although heavily optimized by means of the IndexPool Key Compression pipeline, is somewhat bigger than specialized and very compact models such as Kimi-K3 and DeepSeek-V4-Flash. There is room left for improvements here as well as in terms of decreasing memory consumption further. Future architectural iterations will undoubtedly continue in that direction to ensure the most efficient processing of 1M-token context windows domestically on AI accelerator clusters with the highest possible performance in terms of throughput.

Conclusion

The ability to incorporate visual understanding into the process of coding through using a unique sparse-linear framework allows eliminating the expenses involved in applying complex logic and, hence, the financial barriers of the implementation of AI infrastructure. No matter whether it is managing a sovereign fleet, generating accurate physical CAD, or conducting visual audit of enterprise-wide systems – it offers a completely new paradigm of engineering implementation of AI.

Sources:
blog: https://z.ai/blog/glm-5.3-flash
Guide Document: https://docs.z.ai/guides/vlm/glm-5.3-flash
Model Weights: https://huggingface.co/zai-org/GLM-5.3-Flash


Disclaimer - This article is intended purely for informational purposes. It is not sponsored or endorsed by any company or organization, nor does it serve as an advertisement or promotion for any product or service. All information presented is based on publicly available resources and is subject to change. Readers are encouraged to conduct their own research and due diligence.