AI BENCHY Category Failures
Puzzle Solving: Extra formatting
Puzzle Solving
Extra formatting
See which AI models are most likely to hit Extra formatting on Puzzle Solving, so you can spot weak points faster. Sort by: Response Time (avg) ↑.
Failure Reasons
| Rank | Model | Company | Extra formatting Count | Category Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #77 | Claude Sonnet 4.6 none | Anthropic | 1 | 7.7 | 2/3 | 2.53s |
| #68 | Claude Opus 4.8 none | Anthropic | 1 | 7.7 | 2/3 | 2.74s |
| #51 | Mimo V2 PRO medium | Xiaomi | 1 | 6.4 | 1/3 | 5.08s |
| #113 | DeepSeek V4 Pro none | DeepSeek | 1 | 7.6 | 2/3 | 16.0s |
| #139 | DeepSeek V4 Flash none | DeepSeek | 1 | 3.1 | 0/3 | 23.7s |