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) ↑.
451/451
Filter models
No models match the current search and filters.
| Rank | Model | Company | Puzzle Solving Score | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #171 | Gemini 3.8 Flash low | 1.0 | 0.7 | $0.323 | 3/3 | 2.25s | |
| #305 | Seed 2.1 Turbo none | Bytedance Seed | 1.0 | 0.6 | $0.182 | 3/3 | 2.31s |
| #310 | Solar Pro 4 none | Upstage | 0.5 | 0.6 | $0.022 | 1/3 | 2.33s |
| #18 | Gemini 3.7 Flash medium | 1.0 | 1.0 | $0.278 | 3/3 | 2.33s | |
| #46 | Gemini 3.5 Flash low | 1.0 | 0.9 | $0.752 | 3/3 | 2.35s | |
| #386 | Nemotron 3 Super none | NVIDIA | 0.5 | 0.4 | $0.016 | 1/3 | 2.36s |
| #364 | Mimo V2 Omni medium | Xiaomi | 0.6 | 0.5 | $0.683 | 1/3 | 2.38s |
| #52 | Gemini 3.6 Flash low | 1.0 | 0.9 | $0.363 | 3/3 | 2.38s | |
| #121 | Gemini 3.5 Flash medium | 0.8 | 0.8 | $1.316 | 2/3 | 2.38s | |
| #376 | GLM 5V Turbo none | Z.ai | 0.5 | 0.5 | $0.052 | 1/3 | 2.40s |
| #107 | Claude Opus 4.7 medium | Anthropic | 1.0 | 0.8 | $3.636 | 3/3 | 2.43s |
| #227 | Claude Sonnet 5.5 medium | Anthropic | 0.8 | 0.7 | $1.100 | 2/3 | 2.43s |
| #14 | GPT-6 Astra low | OpenAI | 1.0 | 1.0 | $2.160 | 3/3 | 2.44s |
| #323 | Claude Opus 4.7 none | Anthropic | 1.0 | 0.5 | $0.505 | 3/3 | 2.46s |
| #340 | KAT Coder AIR V2.5 high | Kwaipilot | 0.4 | 0.5 | $0.077 | 0/3 | 2.47s |