Puzzle Solving Ranking
See which AI models perform best on Puzzle Solving, which ones stay reliable, and where the biggest gaps appear. Sort by: Response Time (avg) ↓.
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) |
|---|---|---|---|---|---|---|---|
| #78 | Claude Sonnet 5 medium | Anthropic | 0.8 | 0.9 | $1.438 | 2/3 | 2.98s |
| #198 | Inkling low | Thinkingmachines | 0.6 | 0.7 | $0.293 | 1/3 | 2.97s |
| #267 | Trinity Large Thinking medium | Arcee AI | 0.5 | 0.6 | $0.862 | 0/3 | 2.90s |
| #19 | GPT-6 Sol medium | OpenAI | 1.0 | 0.9 | $0.703 | 3/3 | 2.79s |
| #279 | Seed-2.0-Lite none | Bytedance Seed | 0.5 | 0.6 | $0.114 | 1/3 | 2.78s |
| #9 | Gemini 3.7 Flash high | 1.0 | 1.0 | $0.528 | 3/3 | 2.76s | |
| #74 | Claude Haiku 5.5 low | Anthropic | 0.8 | 0.9 | $0.061 | 2/3 | 2.76s |
| #262 | DeepSeek V4 Flash 0731 none | DeepSeek | 0.3 | 0.6 | $0.053 | 0/3 | 2.74s |
| #195 | Claude Opus 4.8 none | Anthropic | 0.8 | 0.7 | $2.334 | 2/3 | 2.74s |
| #244 | LongCat 2.0 none | Meituan | 0.4 | 0.6 | $0.104 | 0/3 | 2.74s |
| #111 | Gemini 3.8 Flash medium | 1.0 | 0.8 | $0.769 | 3/3 | 2.73s | |
| #251 | Qwen3.5 Plus 2026-02-15 none | Qwen | 0.8 | 0.6 | $0.176 | 2/3 | 2.71s |
| #368 | Laguna S 2.1 low | Poolside | 0.3 | 0.5 | $0.108 | 0/3 | 2.70s |
| #135 | Claude Haiku 5.5 medium | Anthropic | 0.8 | 0.8 | $0.063 | 2/3 | 2.67s |
| #213 | GLM 5.3 Flash low | Z.ai | 0.8 | 0.7 | $0.038 | 2/3 | 2.67s |