Mathematical Reasoning on APEX 2025
16.7AccuracyTRICE-30B
Evaluation Results
| Method | Links | |
|---|---|---|
| TRICE-30BTool Usage=true, Parameter Scale=~30B, Evaluation Protocol=unified2026.05 | 16.7 | |
| TRICE-4BTool Usage=true, Parameter Scale=<10B, Evaluation Protocol=unified2026.05 | 13.9 | |
| GLM-4.7-Flash w/ recipeTool Usage=true, Parameter Scale=~30B, Evaluation Protocol=unified2026.05 | 13.9 | |
| GLM-4.7-FlashTool Usage=true, Parameter Scale=~30B, Evaluation Protocol=unified2026.05 | 11.1 | |
| Nemotron-3-Nano-30B-A3BTool Usage=true, Parameter Scale=~30B, Evaluation Protocol=unified2026.05 | 11.1 | |
| GPT-OSS-20BTool Usage=true, Parameter Scale=~30B, Evaluation Protocol=unified2026.05 | 8.3 | |
| TRICE-4BTool Usage=false, Parameter Scale=<10B, Evaluation Protocol=unified2026.05 | 5.6 | |
| Qwen3-4B-Thinking-2507Tool Usage=false, Parameter Scale=<10B, Evaluation Protocol=unified2026.05 | 2.8 | |
| Qwen3-30B-A3B-Instruct-2507Tool Usage=false, Parameter Scale=~30B, Evaluation Protocol=unified2026.05 | 2.8 | |
| Qwen3.5-4BTool Usage=false, Parameter Scale=<10B, Evaluation Protocol=unified2026.05 | 0 | |
| Qwen3.5-9BTool Usage=false, Parameter Scale=<10B, Evaluation Protocol=unified2026.05 | 0 | |
| Qwen3-30B-A3B-Thinking-2507Tool Usage=false, Parameter Scale=~30B, Evaluation Protocol=unified2026.05 | 0 | |
| Qwen3.5-35B-A3BTool Usage=false, Parameter Scale=~30B, Evaluation Protocol=unified2026.05 | 0 | |
| TRICE-30BTool Usage=false, Parameter Scale=~30B, Evaluation Protocol=unified2026.05 | 0 |