DeepHermes 3 - Mistral 24B vs GPT-5.1
Nous Research vs OpenAI — benchmarks, pricing, and capabilities side by side.
- •GPT-5.1 has the higher intelligence index (89 vs 43.8)
- •DeepHermes 3 - Mistral 24B is cheaper ($0.00 vs $1.25 per 1M input)
| DeepHermes 3 - Mistral 24B | GPT-5.1 | |
|---|---|---|
| Intelligence index | 43.8 | 89 |
| Developer | Nous Research | OpenAI |
| Type | LLM | LLM |
| Access | — | API only |
| Context window | — | 400,000 tokens |
| Input price | $0.00 / 1M | $1.25 / 1M |
| Output price | $0.00 / 1M | $10.00 / 1M |
| Speed | — | 115 tok/s |
| Released | March 13, 2025 | November 12, 2025 |
| Parameters | — | — |
| Input modalities | — | Text, Image |
| Output modalities | — | Text |
Shared benchmarks
DeepHermes 3 - Mistral 24B
GPT-5.1
GPQA Diamond
38.2
88.1
Humanity’s Last Exam
3.9
26.5
LiveCodeBench
19.5
86.8
MMLU-Pro
58
87