Reasoning on ARC Easy (Min/Max/Avg/Voting/ETTC)
97.14Minimum ScoreQwen-3-Thinking Ensemble
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Qwen-3-Thinking EnsembleModels=30B, 235B2026.05 | 97.14 | 97.72 | 97.43 | 98.74 | 98.95 | |
| Qwen-3-Thinking EnsembleModels=4B, 30B2026.05 | 95.99 | 97.14 | 96.56 | 97.69 | 98.78 | |
| Qwen-3-Thinking EnsembleModels=4B, 235B2026.05 | 95.99 | 97.72 | 96.86 | 97.69 | 98.78 | |
| Qwen-3-Thinking EnsembleModels=4B, 30B, 235B2026.05 | 95.99 | 97.72 | 96.95 | 98.91 | 98.99 |