Puzzle Solving Ranking
See which AI models perform best on Puzzle Solving, which ones stay reliable, and where the biggest gaps appear. Sort by: Tests Correct ↓.
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) |
|---|---|---|---|---|---|---|---|
| #244 | Ling-2.6-1T none | Inclusionai | 3.1 | 5.3 | $0.016 | 0/3 | 5.36s |
| #246 | Qwen3.6 35B A3B none | Qwen | 3.2 | 5.3 | $0.051 | 0/3 | 1.07s |
| #247 | Dots 3 Note Preview none | Dots Studio | 3.3 | 5.2 | $0.000 | 0/3 | 1.50s |
| #249 | Granite 4.2 8B medium | IBM Granite | 3.1 | 5.2 | $0.009 | 0/3 | 76.0s |
| #250 | Nemotron 3.5 Lightning medium | NVIDIA | 4.2 | 5.1 | $0.156 | 0/3 | 10.5s |
| #251 | Mistral Small 4 none | Mistral | 3.1 | 5.1 | $0.022 | 0/3 | 399ms |
| #252 | Mistral Small 4 medium | Mistral | 3.4 | 5.1 | $0.097 | 0/3 | 2.17s |
| #253 | Granite 4.2 8B low | IBM Granite | 3.0 | 5.1 | $0.012 | 0/3 | 90.8s |
| #254 | Qwen3 Coder Next none | Qwen | 3.0 | 5.1 | $0.026 | 0/3 | 24.3s |
| #256 | Qwen3.5-9B none | Qwen | 3.2 | 5.1 | $0.021 | 0/3 | 621ms |
| #258 | North Mini Code none | Cohere | 3.5 | 5.1 | $0.000 | 0/3 | 24.4s |
| #261 | Laguna S 2.1 low | Poolside | 3.1 | 5.0 | $0.082 | 0/3 | 2.70s |
| #263 | GPT-4o-mini none | OpenAI | 3.5 | 5.0 | $0.010 | 0/3 | 1.21s |
| #266 | Ling-2.6-flash none | Inclusionai | 2.9 | 4.9 | $0.002 | 0/3 | 6.51s |
| #268 | Hy4 preview none | Tencent | 4.6 | 4.8 | $0.041 | 0/3 | 24.1s |