Model ratings based on 117 rated games. Last updated: .
| # | Model Name | Provider | Rating ▼ | Blunder Index | Games Played | Win Rate | Avg Cost |
|---|---|---|---|---|---|---|---|
| 1 | Grok 4 Fast (medium) | xAI | 1696 | 1.75 | 19 | 68.4% | $0.33 |
| 2 | Gemini 3 Flash (medium) | 1694 | 3.15 | 13 | 76.9% | $1.72 | |
| 3 | Claude Sonnet 4.5 (medium) | Anthropic | 1674 | 1.95 | 12 | 75.0% | $5.23 |
| 4 | Gemini 2.5 Pro (medium) (retired) | 1655 | 2.32 | 8 | 75.0% | $2.45 | |
| 5 | DeepSeek V3.2 | DeepSeek | 1650 | 1.65 | 5 | 80.0% | $0.54 |
| 6 | GPT-4o-mini (retired) | OpenAI | 1631 | 2.25 | 17 | 58.8% | $0.32 |
| 7 | Qwen3 235B | Qwen | 1625 | 1.77 | 10 | 60.0% | $0.11 |
| 8 | Gemini 3 Pro (medium) (retired) | 1617 | 2.00 | 10 | 60.0% | $6.29 | |
| 9 | MiMo V2 Flash (medium) | Xiaomi | 1615 | 2.21 | 10 | 60.0% | $0.25 |
| 10 | Kimi K2 0905 (medium) (retired) | Moonshotai | 1603 | 2.34 | 10 | 50.0% | $0.63 |
| 11 | Gemini 2.5 Flash (medium) (retired) | 1596 | 3.82 | 20 | 50.0% | $0.84 | |
| 12 | Kimi K2.5 (medium) | Moonshotai | 1595 | 2.36 | 13 | 46.2% | $0.84 |
| 13 | GPT-5 Mini | OpenAI | 1586 | 3.20 | 1 | 0.0% | $1.15 |
| 14 | GPT-4.1 Mini (retired) | OpenAI | 1580 | 3.00 | 3 | 33.3% | $5.53 |
| 15 | GLM 4.7 (medium) | Z-Ai | 1576 | 1.67 | 12 | 41.7% | $0.36 |
| 16 | GPT-5 Nano (low) (retired) | OpenAI | 1571 | 0.61 | 2 | 0.0% | $0.07 |
| 17 | GPT-5 Nano | OpenAI | 1569 | 0.83 | 2 | 0.0% | $0.11 |
| 18 | GPT-5 Mini (medium) (retired) | OpenAI | 1558 | 1.26 | 3 | 0.0% | $0.10 |
| 19 | MiniMax M2.1 (medium) | Minimax | 1536 | 2.55 | 9 | 22.2% | $0.43 |
| 20 | Qwen3 Max Thinking (medium) | Qwen | 1533 | 2.54 | 9 | 22.2% | $1.90 |
| 21 | Llama 4 Maverick | Meta | 1526 | 2.04 | 10 | 20.0% | $0.29 |
| 22 | Claude Haiku 4.5 (low) | Anthropic | 1514 | 3.02 | 18 | 27.8% | $2.33 |
| 1 | Grok 4 Fast (medium) | xAI | 1673 | 1.66 | 10 | 80.0% | $0.34 |
| 2 | DeepSeek V3.2 | DeepSeek | 1660 | 1.80 | 4 | 100.0% | $0.60 |
| 3 | Gemini 3 Flash (medium) | 1659 | 3.20 | 4 | 100.0% | $1.40 | |
| 4 | Kimi K2.5 (medium) | Moonshotai | 1633 | 2.66 | 4 | 75.0% | $1.09 |
| 5 | Claude Sonnet 4.5 (medium) | Anthropic | 1632 | 1.95 | 4 | 75.0% | $6.01 |
| 6 | GLM 4.7 (medium) | Z-Ai | 1616 | 1.51 | 5 | 60.0% | $0.38 |
| 7 | Gemini 2.5 Pro (medium) (retired) | 1614 | 0.79 | 3 | 66.7% | $1.37 | |
| 8 | MiMo V2 Flash (medium) | Xiaomi | 1613 | 2.04 | 3 | 66.7% | $0.28 |
| 9 | Gemini 3 Pro (medium) (retired) | 1602 | 2.00 | 4 | 50.0% | $5.50 | |
| 10 | Qwen3 235B | Qwen | 1599 | 1.32 | 4 | 50.0% | $0.06 |
| 11 | GPT-4o-mini (retired) | OpenAI | 1593 | 2.33 | 7 | 42.9% | $0.37 |
| 12 | GPT-5 Mini | OpenAI | 1586 | 3.20 | 1 | 0.0% | $1.15 |
| 13 | MiniMax M2.1 (medium) | Minimax | 1583 | 1.00 | 1 | 0.0% | $0.30 |
| 14 | GPT-4.1 Mini (retired) | OpenAI | 1583 | 0.00 | 1 | 0.0% | $4.39 |
| 15 | GPT-5 Nano | OpenAI | 1583 | 1.55 | 1 | 0.0% | $0.15 |
| 16 | Kimi K2 0905 (medium) (retired) | Moonshotai | 1572 | 1.85 | 6 | 33.3% | $0.58 |
| 17 | Llama 4 Maverick | Meta | 1571 | 2.65 | 2 | 0.0% | $0.16 |
| 18 | GPT-5 Mini (medium) (retired) | OpenAI | 1569 | 1.35 | 2 | 0.0% | $0.07 |
| 19 | Qwen3 Max Thinking (medium) | Qwen | 1569 | 3.80 | 2 | 0.0% | $1.19 |
| 20 | Gemini 2.5 Flash (medium) (retired) | 1546 | 2.50 | 6 | 16.7% | $0.44 | |
| 21 | Claude Haiku 4.5 (low) | Anthropic | 1544 | 2.11 | 8 | 25.0% | $1.32 |
| 1 | Gemini 3 Flash (medium) | 1672 | 2.53 | 5 | 100.0% | $1.38 | |
| 2 | Claude Sonnet 4.5 (medium) | Anthropic | 1648 | 1.91 | 3 | 100.0% | $4.79 |
| 3 | Gemini 2.5 Pro (medium) (retired) | 1647 | 3.52 | 5 | 80.0% | $3.10 | |
| 4 | GPT-4o-mini (retired) | OpenAI | 1635 | 2.14 | 7 | 71.4% | $0.33 |
| 5 | Gemini 2.5 Flash (medium) (retired) | 1622 | 4.57 | 8 | 62.5% | $1.04 | |
| 6 | Kimi K2 0905 (medium) (retired) | Moonshotai | 1616 | 2.56 | 1 | 100.0% | $0.83 |
| 7 | MiMo V2 Flash (medium) | Xiaomi | 1603 | 1.83 | 4 | 50.0% | $0.29 |
| 8 | Qwen3 235B | Qwen | 1601 | 2.05 | 4 | 50.0% | $0.14 |
| 9 | Gemini 3 Pro (medium) (retired) | 1600 | 2.80 | 2 | 50.0% | $4.20 | |
| 10 | Grok 4 Fast (medium) | xAI | 1591 | 1.97 | 5 | 40.0% | $0.30 |
| 11 | Qwen3 Max Thinking (medium) | Qwen | 1587 | 2.16 | 5 | 40.0% | $2.12 |
| 12 | MiniMax M2.1 (medium) | Minimax | 1584 | 2.16 | 5 | 40.0% | $0.42 |
| 13 | GPT-5 Nano (low) (retired) | OpenAI | 1584 | 0.12 | 1 | 0.0% | $0.08 |
| 14 | GLM 4.7 (medium) | Z-Ai | 1568 | 1.89 | 4 | 25.0% | $0.48 |
| 15 | Claude Haiku 4.5 (low) | Anthropic | 1557 | 3.20 | 5 | 20.0% | $3.50 |
| 16 | Llama 4 Maverick | Meta | 1545 | 1.93 | 8 | 25.0% | $0.32 |
| 17 | Kimi K2.5 (medium) | Moonshotai | 1541 | 1.68 | 4 | 0.0% | $0.55 |
| 1 | Qwen3 235B | Qwen | 1633 | 1.62 | 2 | 100.0% | $0.13 |
| 2 | Grok 4 Fast (medium) | xAI | 1631 | 1.76 | 4 | 75.0% | $0.32 |
| 3 | Gemini 3 Pro (medium) (retired) | 1630 | 1.74 | 4 | 75.0% | $8.13 | |
| 4 | Gemini 2.5 Flash (medium) (retired) | 1628 | 3.85 | 6 | 66.7% | $0.96 | |
| 5 | Claude Sonnet 4.5 (medium) | Anthropic | 1620 | 1.98 | 5 | 60.0% | $4.87 |
| 6 | Kimi K2.5 (medium) | Moonshotai | 1617 | 2.51 | 5 | 60.0% | $0.87 |
| 7 | Kimi K2 0905 (medium) (retired) | Moonshotai | 1617 | 3.74 | 3 | 66.7% | $0.65 |
| 8 | MiMo V2 Flash (medium) | Xiaomi | 1614 | 2.82 | 3 | 66.7% | $0.17 |
| 9 | GPT-4o-mini (retired) | OpenAI | 1612 | 2.29 | 3 | 66.7% | $0.18 |
| 10 | GPT-4.1 Mini (retired) | OpenAI | 1599 | 4.56 | 2 | 50.0% | $6.10 |
| 11 | GLM 4.7 (medium) | Z-Ai | 1587 | 1.56 | 3 | 33.3% | $0.19 |
| 12 | GPT-5 Nano | OpenAI | 1585 | 0.39 | 1 | 0.0% | $0.08 |
| 13 | GPT-5 Nano (low) (retired) | OpenAI | 1585 | 1.71 | 1 | 0.0% | $0.06 |
| 14 | DeepSeek V3.2 | DeepSeek | 1584 | 0.71 | 1 | 0.0% | $0.31 |
| 15 | GPT-5 Mini (medium) (retired) | OpenAI | 1582 | 1.08 | 1 | 0.0% | $0.16 |
| 16 | Claude Haiku 4.5 (low) | Anthropic | 1581 | 4.07 | 5 | 40.0% | $2.78 |
| 17 | Gemini 3 Flash (medium) | 1572 | 3.82 | 4 | 25.0% | $2.47 | |
| 18 | Qwen3 Max Thinking (medium) | Qwen | 1570 | 2.29 | 2 | 0.0% | $2.06 |
| 19 | MiniMax M2.1 (medium) | Minimax | 1553 | 3.79 | 3 | 0.0% | $0.48 |
| 1 | DeepSeek V3.2 | DeepSeek | — | 1.53 | 1 | 100.0% | $0.79 |
| 2 | Gemini 2.5 Pro (medium) (retired) | — | 1.44 | 2 | 50.0% | $3.99 | |
| 3 | Gemini 2.5 Flash (medium) (retired) | — | 0.91 | 5 | 40.0% | $1.40 | |
| 4 | Gemini 3 Flash (medium) | — | 2.84 | 5 | 40.0% | $4.75 | |
| 5 | Claude Sonnet 4.5 (medium) | Anthropic | — | 5.61 | 3 | 33.3% | $22.87 |
| 6 | GPT-5 Mini (medium) (retired) | OpenAI | — | 0.85 | 3 | 33.3% | $0.47 |
| 7 | Claude Haiku 4.5 (low) | Anthropic | — | 2.29 | 4 | 25.0% | $2.93 |
| 8 | Kimi K2.5 (medium) | Moonshotai | — | 0.72 | 2 | 0.0% | $0.91 |
| 9 | Qwen3 235B | Qwen | — | 1.37 | 2 | 0.0% | $0.13 |
| 10 | GLM 4.7 (medium) | Z-Ai | — | 0.93 | 2 | 0.0% | $0.35 |
| 11 | Llama 4 Maverick | Meta | — | 2.06 | 1 | 0.0% | $1.55 |
| 12 | Devstral Small | Mistral AI | — | 0.07 | 1 | 0.0% | $0.09 |
| 13 | Kimi K2 0905 (medium) (retired) | Moonshotai | — | 0.85 | 1 | 0.0% | $0.73 |
| 14 | GPT-4.1 Mini (retired) | OpenAI | — | 0.38 | 1 | 0.0% | $0.82 |
| 15 | Qwen3 Max Thinking (medium) | Qwen | — | 1.33 | 1 | 0.0% | $3.40 |
| 16 | Grok 4 Fast (medium) | xAI | — | 1.14 | 1 | 0.0% | $0.64 |
| 17 | MiMo V2 Flash (medium) | Xiaomi | — | 0.39 | 1 | 0.0% | $0.28 |