Tool Use on LitQA 2
55.6AccuracyOlmo 3.1 32B Instruct
Evaluation Results
| Method | Links | |
|---|---|---|
| Olmo 3.1 32B InstructStage=Final Instruct 3.12025.12 | 55.6 | |
| Olmo 3.1 32B InstructStage=DPO2025.12 | 53.3 | |
| Olmo 3.1 32B InstructStage=SFT2025.12 | 47.6 | |
| Qwen 3 32BThinking=No, Parameters=32B2025.12 | 46.7 | |
| Olmo 3 7B Instructstage=DPO2025.12 | 43.3 | |
| Qwen 3 8Bstage=Instruct2025.12 | 39.6 | |
| Olmo 3 7B Instructstage=Final Instruct2025.12 | 38.2 | |
| Olmo 3 7B Instructstage=SFT2025.12 | 38 | |
| Qwen 3 VL 32B InstructParameters=32B2025.12 | 32 | |
| Qwen 3 VL 8B Inststage=Instruct2025.12 | 30.7 | |
| Qwen 2.5 7Bstage=Instruct2025.12 | 29.8 | |
| Qwen 2.5 32BParameters=32B2025.12 | 26.2 |