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 ↑.
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) |
|---|---|---|---|---|---|---|---|
| #247 | Gemini 3.5 Flash Lite low | 0.8 | 0.6 | $0.183 | 2/3 | 1.19s | |
| #250 | Solar Pro 4 high | Upstage | 0.9 | 0.6 | $0.077 | 2/3 | 55.2s |
| #251 | Qwen3.5 Plus 2026-02-15 none | Qwen | 0.8 | 0.6 | $0.176 | 2/3 | 2.71s |
| #252 | Ling 3.1 Flash low | Inclusionai | 0.9 | 0.6 | $0.000 | 2/3 | 32.8s |
| #253 | Claude Opus 4.6 medium | Anthropic | 0.8 | 0.6 | $2.961 | 2/3 | 4.71s |
| #254 | Space Bunny Alpha medium | Stealth | 0.8 | 0.6 | $0.000 | 2/3 | 3.42s |
| #258 | Grok 4.20 medium | X AI | 0.8 | 0.6 | $1.246 | 2/3 | 6.22s |
| #259 | Space Bunny Alpha xhigh | Stealth | 0.8 | 0.6 | $0.000 | 2/3 | 5.45s |
| #261 | GLM 5 Turbo medium | Z.ai | 0.9 | 0.6 | $0.323 | 2/3 | 5.23s |
| #264 | Claude Fable 5.1 low | Anthropic | 0.8 | 0.6 | $3.395 | 2/3 | 4.78s |
| #266 | Beam 1.0 501B A23B high | Reflection | 0.8 | 0.6 | $0.674 | 2/3 | 4.02s |
| #271 | Step 5 Preview medium | Stepfun | 0.8 | 0.6 | $4.136 | 2/3 | 59.9s |
| #273 | KAT-Coder-Pro V2.5 default | Kwaipilot | 0.8 | 0.6 | $0.742 | 2/3 | 3.03s |
| #274 | Apodex 1.1 Mini medium | Apodex | 0.8 | 0.6 | $0.000 | 2/3 | 15.2s |
| #275 | Claude Sonnet 4.6 none | Anthropic | 0.8 | 0.6 | $0.661 | 2/3 | 2.53s |