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) |
|---|---|---|---|---|---|---|---|
| #235 | Solar Pro 4 medium | Upstage | 0.9 | 0.6 | $0.098 | 2/3 | 45.8s |
| #340 | Laguna S 2.1 medium | Poolside | 0.3 | 0.5 | $0.092 | 0/3 | 2.62s |
| #263 | Gemini 3.1 Flash Lite Preview none | 1.0 | 0.6 | $0.090 | 3/3 | 900ms | |
| #205 | Qwen3.5-Flash none | Qwen | 0.3 | 0.7 | $0.089 | 0/3 | 10.9s |
| #142 | Qwen3.8 27B low | Qwen | 0.8 | 0.8 | ~$0.089 | 2/3 | 4.91s |
| #52 | GLM 5.3 Flash max | Z.ai | 0.9 | 0.9 | $0.089 | 2/3 | 5.61s |
| #91 | Claude Haiku 5.5 high | Anthropic | 0.6 | 0.8 | $0.088 | 1/3 | 3.28s |
| #402 | Grok 4.20 Beta default | X AI | 0.8 | 0.4 | $0.087 | 2/3 | 586ms |
| #231 | Laguna XS 2.1 medium | Poolside | 0.5 | 0.6 | $0.083 | 1/3 | 3.43s |
| #155 | DeepSeek V4 Pro 0423 none | DeepSeek | 1.0 | 0.7 | $0.083 | 3/3 | 3.61s |
| #306 | Nemotron 3 Super medium | NVIDIA | 0.3 | 0.6 | $0.081 | 0/3 | 3.15s |
| #280 | Gemini 3.1 Flash Lite minimal | 0.6 | 0.6 | $0.080 | 1/3 | 2.15s | |
| #414 | Command A+ high | Cohere | 0.3 | 0.3 | $0.079 | 0/3 | 86.2s |
| #250 | Solar Pro 4 high | Upstage | 0.9 | 0.6 | $0.077 | 2/3 | 55.2s |
| #331 | KAT Coder AIR V2.5 high | Kwaipilot | 0.4 | 0.5 | $0.077 | 0/3 | 2.47s |