Medical Calculation and Tool Use on MedMCP-Calc Neurology & Psychiatry
60.97CSCalcMate-30B
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| CalcMate-30BParameters=30 B2026.01 | 60.97 | 75.48 | 17.95 | |
| GPT-5Parameters=/2026.01 | 60.2 | 49.15 | 27.87 | |
| Claude Opus 4.5Parameters=/2026.01 | 60.02 | 65.83 | 30.37 | |
| Claude Sonnet 4.5Parameters=/2026.01 | 55.98 | 41.26 | 31.57 | |
| Gemini-2.5-ProParameters=/2026.01 | 50.38 | 35 | 18.95 | |
| GLM-4.7Parameters=355 B2026.01 | 49.46 | 51.19 | 17.1 | |
| CalcMate-4BParameters=4 B2026.01 | 49.08 | 76.87 | 11.76 | |
| Gemini-3-ProParameters=/2026.01 | 48.42 | 47.07 | 21.92 | |
| Deepseek-V3.1Parameters=671 B2026.01 | 43.79 | 44.44 | 7.42 | |
| Kimi-K2-InstructParameters=1 T2026.01 | 38 | 33.55 | 11.08 | |
| Baichuan-M2-32BParameters=32 B2026.01 | 36.02 | 26.44 | 7.4 | |
| Qwen3-235B-Instruct-2507Parameters=235 B2026.01 | 34.6 | 39.49 | 11.03 | |
| Qwen3-235B-Thinking-2507Parameters=235 B2026.01 | 33.63 | 16.39 | 6.87 | |
| Qwen3-Next-80B-ThinkingParameters=80 B2026.01 | 33.08 | 33.23 | 10.77 | |
| Qwen3-Next-80B-InstructParameters=80 B2026.01 | 32.57 | 7.39 | 2.86 | |
| Qwen3-235B thinkingParameters=235 B2026.01 | 32.25 | 17.58 | 6.07 | |
| MedGemma-27B-ITParameters=27 B2026.01 | 28.85 | 15.47 | 1.69 | |
| Qwen3-235B non-thinkingParameters=235 B2026.01 | 26.84 | 33.83 | 7.5 | |
| Qwen3-30B-Thinking-2507Parameters=30 B2026.01 | 22.46 | 13.25 | 4.37 | |
| Qwen3-VL-235BParameters=235B2026.01 | 22.45 | 18.17 | 4.46 | |
| Qwen3-30B-Instruct-2507Parameters=30 B2026.01 | 18.44 | 17.25 | 2.86 | |
| Qwen2.5-72BParameters=72 B2026.01 | 17.75 | 33.06 | 4.14 | |
| Llama-3.1-70BParameters=70 B2026.01 | 16.12 | 14.03 | 0 | |
| Llama-3.3-70BParameters=70 B2026.01 | 15.03 | 12.85 | 4.46 | |
| Qwen3-4B-Instruct-2507Parameters=4 B2026.01 | 12.83 | 6.54 | 3.73 |