Puzzle Solving Ranking
See which AI models perform best on Puzzle Solving, which ones stay reliable, and where the biggest gaps appear. Sort by: Metric ↑.
442/442
Filter models
No models match the current search and filters.
| Rank | Model | Company | Puzzle Solving Score | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #27 | Claude Opus 5 high | Anthropic | 1.0 | 0.9 | $4.524 | 3/3 | 4.66s |
| #28 | Claude Opus 5 medium | Anthropic | 1.0 | 0.9 | $2.870 | 3/3 | 4.27s |
| #29 | Seed 2.1 Turbo low | Bytedance Seed | 1.0 | 0.9 | $1.645 | 3/3 | 23.5s |
| #31 | Claude Opus 5.5 medium | Anthropic | 1.0 | 0.9 | $1.804 | 3/3 | 30.1s |
| #33 | GPT-5.5 medium | OpenAI | 1.0 | 0.9 | $4.809 | 3/3 | 6.76s |
| #34 | Claude Sonnet 5.5 max | Anthropic | 1.0 | 0.9 | $8.557 | 3/3 | 6.17s |
| #35 | Qwen3.8 MAX medium | Qwen | 1.0 | 0.9 | $1.181 | 3/3 | 4.93s |
| #36 | Qwen3.8 Max (0902) high | Qwen | 1.0 | 0.9 | $3.306 | 3/3 | 134.1s |
| #42 | Seed 2.1 Turbo high | Bytedance Seed | 1.0 | 0.9 | $1.892 | 3/3 | 27.3s |
| #45 | Gemini 3.5 Flash low | 1.0 | 0.9 | $0.752 | 3/3 | 2.35s | |
| #46 | Qwen3.8 Max (0902) medium | Qwen | 1.0 | 0.9 | $1.096 | 3/3 | 5.89s |
| #47 | Muse Spark 1.3 medium | Meta | 1.0 | 0.9 | $1.712 | 3/3 | 25.0s |
| #48 | Gemini 3.5 Flash Lite high | 1.0 | 0.9 | $0.624 | 3/3 | 2.09s | |
| #49 | Gemini 4 Argon medium | 1.0 | 0.9 | $0.674 | 3/3 | 2.10s | |
| #50 | Claude Opus 5 low | Anthropic | 1.0 | 0.9 | $2.350 | 3/3 | 4.23s |