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) |
|---|---|---|---|---|---|---|---|
| #76 | Qwen3.8 27B medium | Qwen | 8.3 | 7.8 | ~$0.058 | 2/3 | 12.6s |
| #293 | Grok 4.20 none | X AI | 5.3 | 4.1 | $0.057 | 1/3 | 473ms |
| #214 | Inkling Small low | Thinkingmachines | 5.3 | 5.7 | $0.055 | 1/3 | 1.56s |
| #262 | DeepSeek V3.2 none | DeepSeek | 7.6 | 5.0 | $0.054 | 2/3 | 6.91s |
| #241 | Inkling Small none | Thinkingmachines | 3.2 | 5.3 | $0.054 | 0/3 | 665ms |
| #234 | Laguna S 2.1 medium | Poolside | 3.1 | 5.4 | $0.053 | 0/3 | 2.62s |
| #79 | Qwen3.7 Flash high | Qwen | 7.1 | 7.8 | $0.052 | 1/3 | 10.8s |
| #221 | GLM 5V Turbo none | Z.ai | 5.3 | 5.6 | $0.052 | 1/3 | 2.40s |
| #168 | Gemini 3.1 Flash Lite Preview none | 10.0 | 6.4 | $0.052 | 3/3 | 900ms | |
| #180 | GPT-5.6 Luna low | OpenAI | 7.6 | 6.2 | $0.051 | 2/3 | 3.59s |
| #246 | Qwen3.6 35B A3B none | Qwen | 3.2 | 5.3 | $0.051 | 0/3 | 1.07s |
| #87 | Solar Pro 4 xhigh | Upstage | 8.9 | 7.6 | $0.050 | 2/3 | 58.0s |
| #212 | Nemotron 3 Super medium | NVIDIA | 3.0 | 5.7 | $0.050 | 0/3 | 3.15s |
| #167 | Hy3 preview medium | Tencent | 7.7 | 6.5 | $0.049 | 2/3 | 11.1s |
| #226 | KAT-Coder-Air V2.5 medium | Kwaipilot | 3.6 | 5.6 | $0.048 | 0/3 | 1.87s |