Hermes 3 70B
Hermes 3 70B by Nous Research: Llama-3.1 70B fine-tune with native tool-call and scratchpad tags, 131K token context window, steerable instruct tuning.
Model Overview
Capabilities, design details, and architectural traits
Hermes 3 70B - Llama-3.1 70B fine-tune with native tool
Hermes 3 70B is NousResearch's supervised fine-tune of Meta's Llama-3.1 70B focused on steerable instruction behavior and native tool interaction. The model is configured to accept large contexts and explicit in-prompt control tokens for structured tool calls and internal scratchpad reasoning.
Model-specific notes
- Native tags: The model includes explicit prompt tokens for function/tool invocation and for scratchpad traces, making structured tool-driven workflows part of its documented interface.
- Steerable behavior: The fine-tune mixes role-play, function calling, code, math, and RAG-style traces to produce more controllable outputs compared with an unfine-tuned base model.
Benchmark Performance
Independent evaluations · Artificial Analysis
Accuracy & Capability Details
Compare Models Side-by-Side
Evaluate specifications, pricing, and independent benchmark indices
| Model Details | |||
|---|---|---|---|
| General Info | |||
| Provider | Nous Research | Anthropic | Anthropic |
| Release Date | August 15, 2024 | September 22, 2026 | September 28, 2026 |
| Knowledge Cutoff | Dec 2023 | - | Jun 2026 |
| Context & Limits | |||
| Context Window | 131K | 1M Best Context Window | 1M Best Context Window |
| Pricing (per 1M tokens) | |||
| Input Pricing | $0.70 Best Input Pricing | $4 | $2 |
| Output Pricing | $0.70 Best Output Pricing | $20 | $10 |
| Modalities | |||
| Inputs | text | textimagefile | textimagefile |
| Outputs | text | text | text |
| Benchmarks (0-100) | |||
| Intelligence Index | 6.0 | 57.6 Best Intelligence Index | 56.0 |
| Coding Index | - | - | - |
| Agentic Index | - | - | - |
Humanity's Last Exam
Extremely difficult logical reasoning and knowledge.
SciCode Benchmark
Scientific coding and mathematical modeling.
Long Context Reasoning
Logical reasoning over long context windows.
Independent evaluation data provided by Artificial Analysis. To view the latest benchmarks and full details, visit their official site.
Explore more from Nous Research
Other models by Nous Research
Top AI Models
Leading alternatives by intelligence score
