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) |
|---|---|---|---|---|---|---|---|
| #256 | Trinity Large Thinking low | Arcee AI | 0.6 | 0.6 | $0.918 | 1/3 | 3.28s |
| #260 | KAT-Coder-Pro V2.5 medium | Kwaipilot | 0.6 | 0.6 | $0.669 | 1/3 | 3.20s |
| #269 | Inkling none | Thinkingmachines | 0.6 | 0.6 | $0.292 | 1/3 | 931ms |
| #270 | Qwen3.5 Plus 2026-04-20 none | Qwen | 0.7 | 0.6 | $0.216 | 1/3 | 1.97s |
| #278 | Inkling Small medium | Thinkingmachines | 0.6 | 0.6 | $0.113 | 1/3 | 5.24s |
| #279 | Seed-2.0-Lite none | Bytedance Seed | 0.5 | 0.6 | $0.114 | 1/3 | 2.78s |
| #280 | Gemini 3.1 Flash Lite minimal | 0.6 | 0.6 | $0.080 | 1/3 | 2.15s | |
| #281 | gpt-oss-120b medium | OpenAI | 0.5 | 0.6 | $0.030 | 1/3 | 21.7s |
| #282 | Gemini 3.1 Flash Lite none | 0.6 | 0.6 | $0.069 | 1/3 | 720ms | |
| #284 | Claude Sonnet 5 none | Anthropic | 0.6 | 0.6 | $1.095 | 1/3 | 3.22s |
| #285 | Nemotron 3 Ultra none | NVIDIA | 0.6 | 0.6 | $0.164 | 1/3 | 1.06s |
| #287 | Qwen3.8 Flash Next none | Qwen | 0.6 | 0.6 | ~$0.011 | 1/3 | 1.30s |
| #288 | GPT-5.6 Terra none | OpenAI | 0.5 | 0.6 | $0.377 | 1/3 | 1.23s |
| #289 | DeepSeek V4.1 Flash none | DeepSeek | 0.5 | 0.6 | $0.391 | 1/3 | 1.49s |
| #291 | Ring 2.6 1t medium | Inclusionai | 0.6 | 0.6 | $0.102 | 1/3 | 20.7s |