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) |
|---|---|---|---|---|---|---|---|
| #273 | Grok 4.20 Multi Agent Beta medium | X AI | 6.7 | 4.8 | $5.599 | 1/3 | 5.19s |
| #22 | GPT-5.5 medium | OpenAI | 10.0 | 9.0 | $4.163 | 3/3 | 6.76s |
| #66 | Kimi K3 max | Moonshot AI | 10.0 | 7.9 | $3.467 | 3/3 | 7.36s |
| #20 | Claude Fable 5.1 high | Anthropic | 10.0 | 9.0 | $3.364 | 3/3 | 6.11s |
| #15 | Claude Opus 5 high | Anthropic | 10.0 | 9.2 | $3.070 | 3/3 | 4.66s |
| #39 | Claude Fable 5 medium | Anthropic | 7.7 | 8.6 | $3.004 | 2/3 | 5.18s |
| #82 | Claude Opus 4.6 medium | Anthropic | 7.7 | 7.7 | $2.961 | 2/3 | 4.71s |
| #52 | Claude Fable 5.1 medium | Anthropic | 7.6 | 8.3 | $2.909 | 2/3 | 5.70s |
| #56 | Qwen3.8 2.4T A95B low | Qwen | 10.0 | 8.1 | $2.672 | 3/3 | 43.4s |
| #136 | Claude Fable 5.1 low | Anthropic | 7.7 | 6.9 | $2.565 | 2/3 | 4.78s |
| #105 | Qwen3.8 2.4T A95B high | Qwen | 10.0 | 7.4 | $2.357 | 3/3 | 65.5s |
| #245 | Gemini 3.1 Flash Lite Preview high | 7.7 | 5.3 | $2.310 | 2/3 | 46.7s | |
| #60 | Muse Spark 1.1 high | Meta | 7.8 | 8.0 | $2.253 | 2/3 | 70.0s |
| #24 | Grok 4.5 high | X AI | 10.0 | 9.0 | $2.252 | 3/3 | 7.88s |
| #75 | Claude Sonnet 4.6 medium | Anthropic | 10.0 | 7.8 | $2.126 | 3/3 | 5.31s |