Nous Research

Hermes 4.3 36B

A hybrid-reasoning model for code, STEM, tools, and JSON.

open-weightsreasoningagentscoding

Model record

Hermes 4.3 36B model overview

Hermes 4.3 36B is a open weights model from Nous Research. It was released on December 3, 2025. Its strongest case is 512k context, while buyers should account for no model-specific price.

Hermes 4.3 36B benchmark snapshot

EvaluationReported scoreWhat it probes
MMLU-ProNot reportedBroad knowledge and multi-step reasoning
GPQA DiamondNot reportedGraduate-level science reasoning
SWE-bench VerifiedNot reportedVerified real-repository issue resolution
LiveCodeBenchNot reportedContamination-aware competitive programming
SWE-Bench ProNot reportedLonger, harder professional software tasks
Artificial Analysis Intelligence IndexNot reportedComposite third-party capability index; version matters

Scores are percentages reported by model creators or benchmark maintainers under varying settings. A blank is preferable to an inferred result. See our methodology.

Hermes 4.3 36B strengths

  • 512K context
  • Apache-licensed weights

Hermes 4.3 36B limitations

  • No model-specific price
  • Derived from a ByteDance Seed-OSS base
Editorial take: Benchmark rank should narrow a shortlist, not close a purchase. Run a private evaluation with representative prompts, failure cases, latency targets, and total token costs.

Source record

Specifications and scores are linked to the best source located during review. Provider-reported results are not presented as third-party lab reproductions.

Source limitation: Official model card: https://huggingface.co/NousResearch/Hermes-4.3-36B

Read Nous Research Hermes 4.3 announcement