Puzzle Solving Ranking
See which AI models perform best on Puzzle Solving, which ones stay reliable, and where the biggest gaps appear. Sort by: Metric ↑.
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) |
|---|---|---|---|---|---|---|---|
| #341 | Mimo V2 PRO medium | Xiaomi | 0.6 | 0.5 | $0.333 | 1/3 | 5.08s |
| #307 | Gemma 4 31B none | 0.6 | 0.6 | $0.031 | 1/3 | 4.23s | |
| #168 | Qwen3.5-27B none | Qwen | 0.7 | 0.7 | $0.116 | 1/3 | 1.38s |
| #248 | MiMo-V2.5-Pro medium | Xiaomi | 0.7 | 0.6 | $0.332 | 1/3 | 5.31s |
| #278 | Qwen3.5 Plus 2026-04-20 none | Qwen | 0.7 | 0.6 | $0.216 | 1/3 | 1.97s |
| #400 | Grok 4.20 Multi Agent Beta medium | X AI | 0.7 | 0.4 | $5.599 | 1/3 | 5.19s |
| #347 | MiMo-V2.5-Pro none | Xiaomi | 0.7 | 0.5 | $0.135 | 1/3 | 1.30s |
| #36 | DeepSeek V4.1 Flash 1017 low | DeepSeek | 0.7 | 0.9 | $0.355 | 1/3 | 2.54s |
| #87 | Inkling high | Thinkingmachines | 0.7 | 0.8 | $1.238 | 1/3 | 10.7s |
| #106 | DeepSeek V4 Pro 0423 high | DeepSeek | 0.7 | 0.8 | $0.149 | 1/3 | 56.8s |
| #263 | DeepSeek V3.2 medium | DeepSeek | 0.7 | 0.6 | $0.152 | 1/3 | 37.7s |
| #173 | Qwen3.7 Flash high | Qwen | 0.7 | 0.7 | $0.063 | 1/3 | 10.8s |
| #221 | Qwen3.7 Flash medium | Qwen | 0.7 | 0.7 | $0.076 | 1/3 | 8.30s |
| #140 | Qwen3.7 Flash low | Qwen | 0.7 | 0.8 | $0.071 | 1/3 | 9.79s |
| #66 | GPT-5.2 medium | OpenAI | 0.7 | 0.9 | $1.558 | 2/3 | 5.80s |