Model Leaderboard
1761 models tracked; 1389 have enough benchmark coverage for a unified ELO rating. Top 100 shown below.
| Rank | Model | Provider | Unified ELO | Benchmarks |
|---|---|---|---|---|
| 1 | Claude Fable 5.1 | Anthropic | 1808 ± 1 | 157 |
| 2 | GPT-6 | OpenAI | 1805 ± 1 | 100 |
| 3 | Claude Mythos 5 | Anthropic | 1800 ± 1 | 54 |
| 4 | Gemini 3.8 Flash | 1778 ± 1 | 146 | |
| 5 | Gemini 3.7 Flash | 1774 ± 1 | 267 | |
| 6 | Claude Fable 5 | Anthropic | 1773 ± 1 | 412 |
| 7 | GPT-5.5 Pro | OpenAI | 1773 ± 1 | 55 |
| 8 | GPT-5.6 Pro Sol | OpenAI | 1772 ± 1 | 18 |
| 9 | Claude Opus 5 | Anthropic | 1771 ± 1 | 393 |
| 10 | Muse Spark 1.3 | Meta | 1770 ± 1 | 83 |
| 11 | Claude Mythos Preview | Anthropic | 1767 ± 1 | 79 |
| 12 | GPT-5.6 Sol | OpenAI | 1761 ± 1 | 516 |
| 13 | Kimi K3 | Moonshot | 1754 ± 1 | 403 |
| 14 | GPT-5.4 Pro | OpenAI | 1753 ± 1 | 62 |
| 15 | GPT-5.5 | OpenAI | 1743 ± 1 | 1080 |
| 16 | Gemini 3 Deep Think | 1742 ± 1 | 21 | |
| 17 | Grok 4.6 | xAI | 1741 ± 1 | 226 |
| 18 | Gemini 3.6 Flash | 1737 ± 1 | 299 | |
| 19 | Muse Spark 1.2 | Meta | 1737 ± 1 | 161 |
| 20 | Qwen 3.8 Max | Alibaba | 1735 ± 1 | 228 |
| 21 | Gemini 3.1 Pro (Preview) | 1734 ± 1 | 1142 | |
| 22 | Muse Spark 1.1 | Meta | 1733 ± 1 | 186 |
| 23 | Qwen 3.8 Flash | Alibaba | 1731 ± 1 | 31 |
| 24 | Qwen 3.7 Max | Alibaba | 1729 ± 1 | 248 |
| 25 | Hy4 preview | Other | 1728 ± 1 | 78 |
| 26 | Gemini 3.5 Flash | 1726 ± 1 | 424 | |
| 27 | Qwen3.8-Flash-Next | Alibaba | 1723 ± 1 | 105 |
| 28 | Muse Spark | Meta | 1722 ± 1 | 103 |
| 29 | GPT-5.6 Terra | OpenAI | 1719 ± 1 | 372 |
| 30 | Qwen3.8 2.4T A95B | Alibaba | 1719 ± 1 | 81 |
| 31 | Claude Opus 4.8 | Anthropic | 1718 ± 1 | 826 |
| 32 | Gemini 3 Pro | 1716 ± 1 | 302 | |
| 33 | Grok 4.5 | xAI | 1715 ± 1 | 295 |
| 34 | GLM-5.3 | Zhipu | 1715 ± 1 | 220 |
| 35 | Doubao-Seed-2.0-Pro-260215 | ByteDance | 1715 ± 1 | 8 |
| 36 | GPT-5.2 Pro | OpenAI | 1713 ± 1 | 67 |
| 37 | Gemini 2.5 Pro (Preview) | 1713 ± 1 | 9 | |
| 38 | Seed 2.1 Pro | ByteDance | 1712 ± 1 | 63 |
| 39 | Composer 2.5 | Other | 1712 ± 1 | 9 |
| 40 | DeepSeek V4 Pro (0813) | DeepSeek | 1711 ± 1 | 149 |
| 41 | Qwen 3.7 Max (2026-06-08) | Alibaba | 1710 ± 1 | 7 |
| 42 | Claude Opus 4.7 | Anthropic | 1709 ± 1 | 909 |
| 43 | Gemini 3 Pro (Preview) | 1709 ± 1 | 626 | |
| 44 | DeepSeek-V4-Flash-Vision-Exp | DeepSeek | 1706 ± 1 | 39 |
| 45 | GPT-5.4 | OpenAI | 1704 ± 1 | 1017 |
| 46 | GLM-5.3 Flash | Zhipu | 1704 ± 1 | 192 |
| 47 | Grok 4.20 Multi-Agent | xAI | 1704 ± 1 | 41 |
| 48 | GLM-5.1 FP8 | Zhipu | 1704 ± 1 | 15 |
| 49 | Qwen 3.6 Max Preview | Alibaba | 1703 ± 1 | 146 |
| 50 | Claude Opus 4.6 | Anthropic | 1699 ± 1 | 874 |
| 51 | GPT-5.3 Codex | OpenAI | 1699 ± 1 | 134 |
| 52 | Gemini 3 Flash | 1698 ± 1 | 333 | |
| 53 | GPT-5.4 (2026-03-05) | OpenAI | 1697 ± 1 | 49 |
| 54 | GPT-5 Pro | OpenAI | 1697 ± 1 | 38 |
| 55 | O3 Pro (2025-06-10) | OpenAI | 1697 ± 1 | 7 |
| 56 | Seed 2.1 Turbo | ByteDance | 1696 ± 1 | 39 |
| 57 | Gemini 3 Flash (Preview) | 1695 ± 1 | 569 | |
| 58 | Kimi K2.7 Code | Moonshot | 1695 ± 1 | 141 |
| 59 | DeepSeek V4 Flash (0731) | DeepSeek | 1692 ± 1 | 174 |
| 60 | Ernie 5.1 | Baidu | 1692 ± 1 | 37 |
| 61 | GLM-5.2 | Zhipu | 1691 ± 1 | 398 |
| 62 | Hy3 | Tencent | 1691 ± 1 | 142 |
| 63 | GPT-5 | OpenAI | 1690 ± 1 | 1473 |
| 64 | GPT-5.6 Luna | OpenAI | 1690 ± 1 | 367 |
| 65 | GLM-5 FP8 | Zhipu | 1690 ± 1 | 32 |
| 66 | Claude Sonnet 5 | Anthropic | 1689 ± 1 | 303 |
| 67 | Qwen 3.8 27B | Alibaba | 1689 ± 1 | 187 |
| 68 | GPT-5.2 Codex | OpenAI | 1689 ± 1 | 87 |
| 69 | Qwen 3.7 Plus | Alibaba | 1688 ± 1 | 193 |
| 70 | Grok Build 0.1 | xAI | 1687 ± 1 | 66 |
| 71 | GPT-5.2 ChatGPT | OpenAI | 1686 ± 1 | 9 |
| 72 | Kimi K2.6 | Moonshot | 1685 ± 1 | 609 |
| 73 | Claude Opus 4.5 | Anthropic | 1685 ± 1 | 470 |
| 74 | Qwen 3.6 Max | Alibaba | 1685 ± 1 | 11 |
| 75 | Gemini 2.5 Pro (Preview 06-05) | 1684 ± 1 | 42 | |
| 76 | Gemma 4 | 1684 ± 1 | 15 | |
| 77 | Claude Opus 4.5 (20251101) | Anthropic | 1683 ± 1 | 108 |
| 78 | DeepSeek V4 Pro Preview | DeepSeek | 1683 ± 1 | 12 |
| 79 | GPT-5.2 | OpenAI | 1681 ± 1 | 1214 |
| 80 | Nex N2 Pro | Nex AGI | 1681 ± 1 | 79 |
| 81 | Qwen 3.5 Plus | Alibaba | 1680 ± 1 | 114 |
| 82 | Inkling | Thinking Machines | 1679 ± 1 | 194 |
| 83 | Qwen3 235B A22B Instruct 2507 FP8 | Alibaba | 1679 ± 1 | 7 |
| 84 | GLM-5.1 | Zhipu | 1678 ± 1 | 500 |
| 85 | GPT-5.1 Codex Max | OpenAI | 1676 ± 1 | 41 |
| 86 | O3 Pro | OpenAI | 1675 ± 1 | 35 |
| 87 | Doubao-1.8-Pro | ByteDance | 1675 ± 1 | 21 |
| 88 | Seed 2.0 Pro | ByteDance | 1674 ± 1 | 54 |
| 89 | O3 | OpenAI | 1672 ± 1 | 403 |
| 90 | DeepSeek-V4-Flash-FP8 | DeepSeek | 1672 ± 1 | 15 |
| 91 | Qwen 3.6 Plus | Alibaba | 1671 ± 1 | 587 |
| 92 | MiMo-V2.5-Pro | Xiaomi | 1671 ± 1 | 250 |
| 93 | GPT-5 Codex | OpenAI | 1671 ± 1 | 63 |
| 94 | Claude Sonnet 4.6 | Anthropic | 1670 ± 1 | 1243 |
| 95 | Qwen 3.5 397B A17B | Alibaba | 1670 ± 1 | 421 |
| 96 | NVIDIA-Nemotron-3-Super-120B-A12B-FP8 | NVIDIA | 1670 ± 1 | 12 |
| 97 | Inkling Small | Thinking Machines | 1669 ± 1 | 171 |
| 98 | GPT-5.1 Codex | OpenAI | 1668 ± 1 | 84 |
| 99 | GPT-5.3 | OpenAI | 1667 ± 1 | 281 |
| 100 | O3 (2025-04-16) | OpenAI | 1665 ± 1 | 248 |
Interactive version: theaggregate.ai/models · How It Works · Data refreshed daily, snapshot 2026-09-05.