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) |
|---|---|---|---|---|---|---|---|
| #223 | Gemma 4 26B A4B none | 6.2 | 5.6 | $0.015 | 1/3 | 744ms | |
| #224 | Mimo V2 PRO none | Xiaomi | 6.0 | 5.6 | $0.045 | 1/3 | 1.61s |
| #225 | Owl Alpha none | Openrouter | 5.4 | 5.6 | $0.000 | 1/3 | 4.18s |
| #229 | Qwen3.6 27B none | Qwen | 5.3 | 5.5 | $0.116 | 1/3 | 5.15s |
| #230 | Hy3 preview low | Tencent | 5.3 | 5.5 | $0.042 | 1/3 | 7.51s |
| #231 | Qwen3.8 27B none | Qwen | 6.0 | 5.5 | ~$0.006 | 1/3 | 1.25s |
| #236 | GPT-5.6 Luna none | OpenAI | 5.3 | 5.4 | $0.029 | 1/3 | 790ms |
| #237 | MiMo-V2.5-Pro none | Xiaomi | 6.7 | 5.4 | $0.068 | 1/3 | 1.30s |
| #248 | Inkling none | Thinkingmachines | 5.6 | 5.2 | $0.147 | 1/3 | 931ms |
| #255 | MiMo-V2.5 none | Xiaomi | 5.4 | 5.1 | $0.025 | 1/3 | 2.13s |
| #257 | GLM 5 Turbo none | Z.ai | 5.5 | 5.1 | $0.047 | 1/3 | 2.65s |
| #259 | MiniMax M2.7 medium | Minimax | 5.9 | 5.0 | $0.208 | 1/3 | 24.9s |
| #264 | Qwen3.6 Plus Preview medium | Qwen | 5.3 | 4.9 | $0.000 | 1/3 | 7.52s |
| #265 | Mercury 2.5 Preview none | Inception | 5.6 | 4.9 | $0.018 | 1/3 | 684ms |
| #267 | Nemotron 3 Super none | NVIDIA | 5.5 | 4.8 | $0.008 | 1/3 | 2.36s |