Hermes 3 70B Instruct
Nous Research · released Aug 18, 2024
Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...
Specification
- Context window
- 131K
- Max output
- 16K
- Knowledge cutoff
- Dec 31, 2023
- Parameters
- 70.6B
- Licence
- llama3
- Serving providers
- 1
- Moderated
- No
- Uptime
- 100.0%
Intelligence
4.8
16th percentile
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
34 t/s
Median across providers
Latency
344ms
Time to first token
Cost per task
$0.05
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- MMLU-Pro57.1%
- GPQA Diamond40.1%
- SciCode23.1%
- LiveCodeBench18.8%
- Humanity's Last Exam4.0%
- AIME 20252.3%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| MMLU-Pro | 57.1% |
| GPQA Diamond | 40.1% |
| SciCode | 23.1% |
| LiveCodeBench | 18.8% |
| Humanity's Last Exam | 4.0% |
| AIME 2025 | 2.3% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- SabaMistral AI6.2
- Olmo 3 32B ThinkAllen AI6.1
- Hermes 3 70B InstructNous Research4.8
- Phi 4Microsoft4.6
- Mistral LargeMistral AI4.1
- Mixtral 8x22B InstructMistral AI4.0
- Reka Flash 3Reka AI3.7
- Claude 3 HaikuAnthropic3.5
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Saba | 6.2 |
| Olmo 3 32B Think | 6.1 |
| Hermes 3 70B Instruct | 4.8 |
| Phi 4 | 4.6 |
| Mistral Large | 4.1 |
| Mixtral 8x22B Instruct | 4.0 |
| Reka Flash 3 | 3.7 |
| Claude 3 Haiku | 3.5 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.7
- Output / 1M tokens
- $0.7
- Cached input / 1M
- Not offered
- Blended 3:1
- $0.7
One task, estimated
$0.05
- Input tokens
- 50,000
- Output tokens
- 25,000
- Profile
- Standard
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.