Science Reasoning on ARC-C English (test)
95AccuracyClaude 3.7 Sonnet
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude 3.7 Sonnet2026.06 | 95 | |
| LuckyStar 111B2026.06 | 93.8 | |
| Command A2026.06 | 93.4 | |
| Qwen3 235B A22B2026.06 | 93.2 | |
| LuckyStar 111BQuantization=4-bit2026.06 | 92.8 | |
| GPT-4o2026.06 | 91.8 |