Puzzle Solving Ranking
See which AI models perform best on Puzzle Solving, which ones stay reliable, and where the biggest gaps appear. Sort by: Tests Correct ↓.
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) |
|---|---|---|---|---|---|---|---|
| #144 | Solar Pro 4 medium | Upstage | 9.0 | 6.8 | $0.047 | 2/3 | 45.8s |
| #148 | Gemini 3 Flash Preview none | 7.7 | 6.8 | $0.085 | 2/3 | 1.05s | |
| #150 | GLM 5.2 none | Z.ai | 7.7 | 6.7 | $0.153 | 2/3 | 3.31s |
| #151 | KAT-Coder-Pro V2.5 none | Kwaipilot | 8.2 | 6.7 | $0.487 | 2/3 | 3.03s |
| #154 | GLM 5V Turbo medium | Z.ai | 7.7 | 6.7 | $0.457 | 2/3 | 10.2s |
| #157 | Gemini 3.5 Flash Lite low | 7.6 | 6.6 | $0.138 | 2/3 | 1.19s | |
| #162 | Qwen3.6 35B A3B medium | Qwen | 8.0 | 6.6 | $0.672 | 2/3 | 5.95s |
| #164 | Qwen3.5 Plus 2026-02-15 none | Qwen | 7.7 | 6.6 | $0.073 | 2/3 | 2.71s |
| #165 | Qwen3.6 27B medium | Qwen | 7.7 | 6.5 | $1.045 | 2/3 | 61.1s |
| #167 | Hy3 preview medium | Tencent | 7.7 | 6.5 | $0.049 | 2/3 | 11.1s |
| #173 | MiMo-V2.5 medium | Xiaomi | 8.2 | 6.4 | $0.104 | 2/3 | 20.3s |
| #177 | MiMo-V2-Flash medium | Xiaomi | 7.7 | 6.3 | $0.043 | 2/3 | 3.87s |
| #180 | GPT-5.6 Luna low | OpenAI | 7.6 | 6.2 | $0.051 | 2/3 | 3.59s |
| #183 | Qwen3.5-35B-A3B medium | Qwen | 8.2 | 6.1 | $1.140 | 2/3 | 33.1s |
| #187 | Qwen3.5-Flash medium | Qwen | 8.2 | 6.1 | $0.142 | 2/3 | 27.6s |