Hermes 4.3 36B model card (Hugging Face) 3 Dec 2025
Hermes 4.3 36B
Hermes 4.3 36B ranks first on OpenBookQA.
13
Benchmarks with a score
1
Ranked first, out of five or more models
2
In the top three
Nous Research Dec 2025
Hermes 4.3 36B
Open weights Mid-size
No Epoch Capabilities Index score yet
- MMLU-Pro 80.7% #70 /151
- AIME 2025 69.3% #113 /143
- IFEval 77.9% #103 /126
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenBookQA | 96.6% | #1 of 20 | Model card | |
| MMLU | 87.7% | #30 of 127 | Model card | |
| BIG-Bench Hard | 86.4% | #18 of 71 | Model card | |
| DROP | 83.5% | #18 of 40 | Model card | |
| MMLU-Pro | 80.7% | #70 of 151 | Model card | |
| MuSR | 69.7% | #3 of 6 | Model card | |
| IFEval | 77.9% | #103 of 126 | Model card | |
| SimpleQA | 6.00% | #56 of 59 | Model card |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GPQA Diamond | 65.5% | #192 of 284 | Model card | |
| AIME 2024 | 71.9% | #59 of 87 | Model card | |
| MATH-500 | 93.8% | #46 of 67 | Model card | |
| AIME 2025 | 69.3% | #113 of 143 | Model card |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| RefusalBench (Nous Research) | 74.6% | #1 of 2 | Model card |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.