Puzzle Solving Ranking
See which AI models perform best on Puzzle Solving, which ones stay reliable, and where the biggest gaps appear. Sort by: Total Cost ↓.
311/311
Filter models
No models match the current search and filters.
| Rank | Model | Company | Puzzle Solving Score | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #130 | GPT-5.5 none | OpenAI | 7.7 | 7.0 | $0.544 | 2/3 | 1.29s |
| #30 | Gemini 3.5 Flash Lite high | 10.0 | 8.8 | $0.540 | 3/3 | 2.09s | |
| #93 | GPT 5.3 Chat none | OpenAI | 10.0 | 7.5 | $0.533 | 3/3 | 2.99s |
| #74 | GPT-5.6 Terra medium | OpenAI | 8.4 | 7.8 | $0.523 | 2/3 | 3.78s |
| #58 | Muse Glimmer 30B xhigh | Meta | 7.8 | 8.1 | $0.510 | 2/3 | 199.7s |
| #9 | GPT-5.6 Sol medium | OpenAI | 8.2 | 9.4 | $0.508 | 2/3 | 2.98s |
| #117 | KAT-Coder-Pro V2.5 high | Kwaipilot | 8.2 | 7.2 | $0.506 | 2/3 | 3.38s |
| #156 | Claude Opus 4.7 none | Anthropic | 10.0 | 6.6 | $0.505 | 3/3 | 2.46s |
| #104 | LongCat 2.0 medium | Meituan | 5.4 | 7.4 | $0.499 | 1/3 | 8.84s |
| #68 | Step 3.7 Flash medium | Stepfun | 5.7 | 7.9 | $0.495 | 1/3 | 6.19s |
| #155 | LongCat 2.0 high | Meituan | 3.1 | 6.7 | $0.492 | 0/3 | 9.18s |
| #83 | DeepSeek V4 Pro high | DeepSeek | 6.9 | 7.7 | $0.489 | 1/3 | 56.8s |
| #151 | KAT-Coder-Pro V2.5 none | Kwaipilot | 8.2 | 6.7 | $0.487 | 2/3 | 3.03s |
| #134 | Kimi K2.5 medium | Moonshot AI | 5.3 | 7.0 | $0.479 | 1/3 | 43.2s |
| #135 | KAT-Coder-Pro V2.5 medium | Kwaipilot | 5.9 | 6.9 | $0.478 | 1/3 | 3.20s |