Leaderboard
Frontier AI models ranked by chess understanding and puzzle solving ability.
* Partial run: Models marked with * were tested on Semantic only (400 questions). Full 900-question runs include both Semantic and Position Judgment categories.
| # | Model | Provider | Understanding | Puzzle Solving | Puzzle ELO | Cost / 1K Q |
|---|---|---|---|---|---|---|
| 1 | Claude Opus 4.6400Q semantic only | Anthropic | 83.5%* | Coming Soon | Coming Soon | $20.10 |
| 2 | GPT-5.2400Q semantic only | OpenAI | 78.8%* | Coming Soon | Coming Soon | $25.48 |
| 3 | Claude Sonnet 4.5400Q semantic only | Anthropic | 73.0%* | Coming Soon | Coming Soon | $9.87 |
| 4 | Gemini 3 Flash | 58.6% | Coming Soon | Coming Soon | $1.87 | |
| 5 | GPT-5 Nano | OpenAI | 33.0% | Coming Soon | Coming Soon | $0.69 |
Cost vs. Understanding
How much chess knowledge do you get per dollar?