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) |
|---|---|---|---|---|---|---|---|
| #378 | KAT Coder AIR V2.5 default | Kwaipilot | 0.3 | 0.4 | $0.070 | 0/3 | 1.84s |
| #363 | Qwen3 Coder Next medium | Qwen | 0.3 | 0.5 | $0.071 | 0/3 | 1.25s |
| #137 | Qwen3.7 Flash low | Qwen | 0.7 | 0.8 | $0.071 | 1/3 | 9.79s |
| #167 | Qwen3.8 27B medium | Qwen | 0.8 | 0.7 | ~$0.073 | 2/3 | 12.6s |
| #418 | Command A+ low | Cohere | 0.3 | 0.3 | $0.073 | 0/3 | 95.8s |
| #132 | GPT-6 Luna high | OpenAI | 0.8 | 0.8 | $0.074 | 2/3 | 7.51s |
| #216 | Qwen3.7 Flash medium | Qwen | 0.7 | 0.7 | $0.076 | 1/3 | 8.30s |
| #331 | KAT Coder AIR V2.5 high | Kwaipilot | 0.4 | 0.5 | $0.077 | 0/3 | 2.47s |
| #250 | Solar Pro 4 high | Upstage | 0.9 | 0.6 | $0.077 | 2/3 | 55.2s |
| #414 | Command A+ high | Cohere | 0.3 | 0.3 | $0.079 | 0/3 | 86.2s |
| #280 | Gemini 3.1 Flash Lite minimal | 0.6 | 0.6 | $0.080 | 1/3 | 2.15s | |
| #306 | Nemotron 3 Super medium | NVIDIA | 0.3 | 0.6 | $0.081 | 0/3 | 3.15s |
| #155 | DeepSeek V4 Pro 0423 none | DeepSeek | 1.0 | 0.7 | $0.083 | 3/3 | 3.61s |
| #231 | Laguna XS 2.1 medium | Poolside | 0.5 | 0.6 | $0.083 | 1/3 | 3.43s |
| #402 | Grok 4.20 Beta default | X AI | 0.8 | 0.4 | $0.087 | 2/3 | 586ms |