General Capability Evaluation on OlmoBaseEval LBPP BBH MMLU Pro MC Deepmind Math (HeldOut)
42.6LBPP ScoreSeed 36B
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Seed 36BModel Category=Open-weight, Number of Parameters=36B2025.12 | 42.6 | 85 | 62.2 | 31.3 | |
| Qwen 2.5 32BModel Category=Open-weight, Number of Parameters=32B2025.12 | 40.3 | 81.1 | 61.1 | 40.7 | |
| Nemo-Nano 9BOpenness=Open-weight, Parameters=9B2025.12 | 31.7 | 77 | 50.2 | 31.4 | |
| Mistral 3.1 24BModel Category=Open-weight, Number of Parameters=24B2025.12 | 30.3 | 81.4 | 58.9 | 35.3 | |
| Qwen2 7BOpenness=Open-weight, Parameters=7B2025.12 | 25.7 | 76.5 | 50.3 | 47.7 | |
| Qwen 2.5 7BOpenness=Open-weight, Parameters=7B2025.12 | 22.1 | 54.7 | 48.1 | 32.8 | |
| Olmo 3 32BModel Category=Fully-open, Number of Parameters=32B2025.12 | 21.8 | 77.6 | 49.7 | 29.6 | |
| MiMo 7BOpenness=Open-weight, Parameters=7B2025.12 | 21.5 | 75.1 | 44.3 | 25.4 | |
| Gemma 2 27BModel Category=Open-weight, Number of Parameters=27B2025.12 | 19.7 | 74.8 | 47.6 | 27.6 | |
| Granite 3.3 8BOpenness=Open-weight, Parameters=8B2025.12 | 18.5 | 61.5 | 33.9 | 32.2 | |
| Gemma 3 27BModel Category=Open-weight, Number of Parameters=27B2025.12 | 17.7 | 77.4 | 53.1 | 30.4 | |
| Marin 32BModel Category=Fully-open, Number of Parameters=32B2025.12 | 17.3 | 70.1 | 48.1 | 26.7 | |
| Olmo 3 7BOpenness=Fully-open, Parameters=7B2025.12 | 17.1 | 63.5 | 37.3 | 23.7 | |
| LLM 360 K2V2 70BModel Category=Fully-open, Number of Parameters=70B2025.12 | 13.4 | 73.2 | 45.3 | 32.5 | |
| Gemma 2 9BOpenness=Open-weight, Parameters=9B2025.12 | 12.4 | 68.8 | 44.7 | 23 | |
| Llama 3.1 70BModel Category=Open-weight, Number of Parameters=70B2025.12 | 11.8 | 80.8 | 50.4 | 40.2 | |
| Llama 3.1 8BOpenness=Open-weight, Parameters=8B2025.12 | 9.1 | 63 | 37.4 | 24.1 | |
| OLMo 2 32BModel Category=Fully-open, Number of Parameters=32B2025.12 | 8.2 | 64.6 | 46.9 | 22 | |
| Apertus 70BModel Category=Fully-open, Number of Parameters=70B2025.12 | 8.1 | 58.8 | 39.6 | 20.1 | |
| Apertus 8BOpenness=Fully-open, Parameters=8B2025.12 | 7.1 | 48.1 | 33.9 | 17.1 | |
| Marin 8BOpenness=Fully-open, Parameters=8B2025.12 | 5.8 | 55.6 | 38.8 | 20.2 | |
| Gaperon 8BOpenness=Fully-open, Parameters=8B2025.12 | 4.7 | 38.4 | 20.8 | 34.1 | |
| Gaperon 24BModel Category=Fully-open, Number of Parameters=24B2025.12 | 4.3 | 36.6 | 21.3 | 28.3 | |
| OLMo 2 7BOpenness=Fully-open, Parameters=7B2025.12 | 3.1 | 49.6 | 33.1 | 16.2 |