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 ↑.
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) |
|---|---|---|---|---|---|---|---|
| #147 | Seed-2.0-Code high | Bytedance Seed | 0.8 | 0.7 | $1.448 | 2/3 | 15.9s |
| #219 | Step 3.7 Flash high | Stepfun | 0.5 | 0.7 | $1.478 | 1/3 | 10.2s |
| #184 | Ember-1 low | Fireworks | 1.0 | 0.7 | $1.488 | 3/3 | 3.27s |
| #72 | Claude Sonnet 5.5 xhigh | Anthropic | 1.0 | 0.9 | $1.516 | 3/3 | 4.88s |
| #41 | Pareto default | Unbiased | 0.8 | 0.9 | $1.520 | 2/3 | 18.2s |
| #144 | GLM 5.1 medium | Z.ai | 0.8 | 0.8 | $1.546 | 2/3 | 31.6s |
| #65 | GPT-5.2 medium | OpenAI | 0.7 | 0.9 | $1.558 | 2/3 | 5.80s |
| #85 | Gemini 3.1 Pro Preview medium | 1.0 | 0.8 | $1.585 | 3/3 | 6.90s | |
| #55 | Muse Spark 1.2 medium | Meta | 0.9 | 0.9 | $1.590 | 2/3 | 9.45s |
| #196 | Kimi K2.6 medium | Moonshot AI | 0.6 | 0.7 | $1.594 | 1/3 | 25.1s |
| #22 | GPT-5.6 Sol high | OpenAI | 1.0 | 0.9 | $1.595 | 3/3 | 4.10s |
| #43 | Muse Wonder minimal | Meta | 0.5 | 0.9 | $1.639 | 1/3 | 1.36s |
| #29 | Seed 2.1 Turbo low | Bytedance Seed | 1.0 | 0.9 | $1.645 | 3/3 | 23.5s |
| #56 | Muse Spark 1.1 medium | Meta | 0.8 | 0.9 | $1.665 | 2/3 | 42.5s |
| #79 | Qwen3.7 Max medium | Qwen | 1.0 | 0.9 | $1.689 | 3/3 | 8.84s |