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: Failure Count ↑.
Failure Reasons
14/14
Filter models
No models match the current search and filters.
| Rank | Model | Company | Extra formatting Count | Category Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #102 | Claude Opus 5 none | Anthropic | 1 | 7.7 | $1.550 | 2/3 | 3.66s |
| #121 | Claude Sonnet 4.6 none | Anthropic | 1 | 7.7 | $0.661 | 2/3 | 2.53s |
| #128 | Claude Opus 4.8 none | Anthropic | 1 | 7.7 | $1.166 | 2/3 | 2.74s |
| #156 | Seed-2.0-Code medium | Bytedance Seed | 1 | 8.2 | $1.153 | 2/3 | 34.3s |
| #187 | LongCat 2.0 none | Meituan | 1 | 4.0 | $0.044 | 0/3 | 2.74s |
| #191 | Mimo V2 PRO medium | Xiaomi | 1 | 6.4 | $0.333 | 1/3 | 5.08s |
| #196 | Claude Sonnet 5 none | Anthropic | 1 | 6.0 | $0.548 | 1/3 | 3.22s |
| #248 | DeepSeek V4 Flash 0423 none | DeepSeek | 1 | 3.1 | $0.040 | 0/3 | 23.7s |
| #252 | GPT-5.6 Luna none | OpenAI | 1 | 5.3 | $0.029 | 1/3 | 790ms |
| #255 | DeepSeek V4 Flash 0731 none | DeepSeek | 1 | 3.2 | $0.009 | 0/3 | 2.74s |
| #256 | Laguna S 2.1 high | Poolside | 1 | 2.9 | $0.114 | 0/3 | 1.62s |
| #264 | Inkling none | Thinkingmachines | 1 | 5.6 | $0.147 | 1/3 | 931ms |
| #278 | Laguna S 2.1 low | Poolside | 1 | 3.1 | $0.082 | 0/3 | 2.70s |
| #308 | Granite 4.2 8B none | IBM Granite | 1 | 3.0 | $0.037 | 0/3 | 107.6s |