Puzzle Solving Ranking
See which AI models perform best on Puzzle Solving, which ones stay reliable, and where the biggest gaps appear. Sort by: Response Time (avg) ↓.
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 |
| #173 | Step 3.7 Flash low | Stepfun | 0.6 | 0.7 | $0.449 | 1/3 | 1.84s |
| #164 | Gemini 3.5 Flash Lite medium | 0.8 | 0.7 | $0.440 | 2/3 | 1.82s | |
| #436 | LFM2-24B-A2B default | Liquid | 0.4 | 0.2 | $0.001 | 0/3 | 1.78s |
| #112 | Qwen3.8 Flash Next low | Qwen | 0.9 | 0.8 | ~$0.045 | 2/3 | 1.72s |
| #128 | Qwen3.7 Plus none | Qwen | 0.8 | 0.8 | $0.178 | 2/3 | 1.71s |
| #248 | Gemini 3.1 Flash Lite Preview low | 1.0 | 0.6 | $0.736 | 3/3 | 1.69s | |
| #277 | MiMo-V2.6-Pro none | Xiaomi | 0.8 | 0.6 | $0.193 | 2/3 | 1.67s |
| #437 | Solar Decide Flash default | Upstage | 1.0 | 0.2 | $0.003 | 0/1 | 1.66s |
| #349 | Laguna S 2.1 high | Poolside | 0.3 | 0.5 | $0.145 | 0/3 | 1.62s |
| #371 | Mimo V2 PRO default | Xiaomi | 0.6 | 0.5 | $0.045 | 1/3 | 1.61s |
| #345 | KAT Coder AIR V2.5 low | Kwaipilot | 0.3 | 0.5 | $0.046 | 0/3 | 1.57s |
| #328 | Inkling Small low | Thinkingmachines | 0.5 | 0.5 | $0.055 | 1/3 | 1.56s |
| #343 | Dots 3 Note Preview default | Dots Studio | 0.3 | 0.5 | $0.000 | 0/3 | 1.50s |
| #211 | GPT-5.6 Sol none | OpenAI | 0.8 | 0.7 | $0.795 | 2/3 | 1.49s |