Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...
Tested on 6 benchmarks · BenchGecko score 73.2. Top scores: IFEval (76.6%), BBH (HuggingFace) (53.8%), MMLU-PRO (41.4%).
gpt-oss-120b (free) scores 74.2 (101% as good) at $0.00/1M input · 100% cheaper
HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.
HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.
HuggingFace MMLU-Pro. Harder version of MMLU with 10 answer choices instead of 4 and more challenging questions.
HuggingFace evaluation of GPQA (Graduate-Level Google-Proof Q&A). PhD-level science questions that cannot be easily searched.
- Typetext
- Context131K tokens (~66 books)
- ReleasedAug 2024
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.002
Frequently Asked Questions
Key facts · as of 2026-10-05
- Hermes 3 70B Instruct by nousresearch. BenchGecko score 73.2, rank 30 of 312 scored models (normalized average of public benchmark scores).
- List price $0.70 input · $0.70 output per 1M tokens (as of 2026-10-05).
- Sold by 1 provider (as of 2026-10-05): DeepInfra (fp8) $0.70 in / $0.70 out.
How to cite · data as of 2026-10-05
Hermes 3 70B Instruct · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/hermes-3-llama-3-1-70b
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP