Puzzle Solving Ranking
See which AI models perform best on Puzzle Solving, which ones stay reliable, and where the biggest gaps appear. Sort by: Total Cost ↑.
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) |
|---|---|---|---|---|---|---|---|
| #193 | Nemotron 3 Ultra none | NVIDIA | 5.9 | 6.1 | $0.084 | 1/3 | 1.06s |
| #62 | DeepSeek V4 Flash 0731 high | DeepSeek | 8.2 | 8.0 | $0.084 | 2/3 | 9.36s |
| #148 | Gemini 3 Flash Preview none | 7.7 | 6.8 | $0.085 | 2/3 | 1.05s | |
| #286 | Grok 4.20 Beta none | X AI | 7.7 | 4.4 | $0.087 | 2/3 | 586ms |
| #208 | Seed 2.1 Turbo none | Bytedance Seed | 10.0 | 5.9 | $0.092 | 3/3 | 2.31s |
| #149 | Gemma 4 26B A4B medium | 10.0 | 6.8 | $0.092 | 3/3 | 5.79s | |
| #131 | Mercury 2 medium | Inception | 5.4 | 7.0 | $0.094 | 1/3 | 949ms |
| #207 | GPT-5.4 Mini none | OpenAI | 5.4 | 5.9 | $0.095 | 1/3 | 836ms |
| #252 | Mistral Small 4 medium | Mistral | 3.4 | 5.1 | $0.097 | 0/3 | 2.17s |
| #179 | Gemma 4 31B medium | 9.9 | 6.2 | $0.100 | 3/3 | 26.9s | |
| #238 | Kimi K2.5 none | Moonshot AI | 3.0 | 5.4 | $0.101 | 0/3 | 4.04s |
| #175 | Ring-2.6-1T medium | Inclusionai | 5.9 | 6.4 | $0.102 | 1/3 | 20.7s |
| #173 | MiMo-V2.5 medium | Xiaomi | 8.2 | 6.4 | $0.104 | 2/3 | 20.3s |
| #113 | Qwen3.7 Plus none | Qwen | 7.7 | 7.3 | $0.106 | 2/3 | 1.71s |
| #160 | Inkling Small medium | Thinkingmachines | 5.8 | 6.6 | $0.113 | 1/3 | 5.24s |