Model Leaderboard
1776 models tracked; 1776 have enough benchmark coverage for a unified ELO rating. Top 100 shown below.
| Rank | Model | Provider | Unified ELO | Benchmarks |
|---|---|---|---|---|
| 1 | Human Expert | Human | 2500 ± 48 | 59 |
| 2 | GPT-5.5 Pro (xHigh) | OpenAI | 2268 ± 57 | 12 |
| 3 | Claude Mythos 5 | Anthropic | 2250 ± 31 | 57 |
| 4 | Gemini 3 Deep Think | 2186 ± 71 | 18 | |
| 5 | GPT-5.6 Sol (Max) | OpenAI | 2175 ± 48 | 38 |
| 6 | Claude Fable 5 (Max) | Anthropic | 2173 ± 37 | 27 |
| 7 | Claude Opus 4.6 (Medium) | Anthropic | 2129 ± 131 | 7 |
| 8 | Claude Fable 5 (High) | Anthropic | 2104 ± 41 | 18 |
| 9 | Claude Mythos Preview | Anthropic | 2103 ± 21 | 79 |
| 10 | GPT-5.6 Sol (xHigh) | OpenAI | 2096 ± 39 | 42 |
| 11 | GPT-5.5 Pro | OpenAI | 2092 ± 63 | 29 |
| 12 | Claude Fable 5 | Anthropic | 2088 ± 25 | 140 |
| 13 | GPT-5.5 (xHigh) | OpenAI | 2057 ± 17 | 109 |
| 14 | GPT-5.6 Terra (Max) | OpenAI | 2051 ± 39 | 31 |
| 15 | GPT-5.6 Sol (High) | OpenAI | 2041 ± 33 | 28 |
| 16 | Kimi K3 (Max) | Moonshot | 2034 ± 52 | 11 |
| 17 | GPT-5.4 Pro (xHigh) | OpenAI | 2019 ± 27 | 63 |
| 18 | GPT-5.6 Sol (Medium) | OpenAI | 2016 ± 31 | 23 |
| 19 | GPT-5.2 (xHigh) | OpenAI | 2012 ± 26 | 85 |
| 20 | GPT-5.5 (High) | OpenAI | 2011 ± 26 | 66 |
| 21 | Claude Opus 4.7 (Max) | Anthropic | 2007 ± 42 | 17 |
| 22 | Claude Sonnet 5 (Max) | Anthropic | 2007 ± 34 | 9 |
| 23 | Claude Opus 4.8 (Max) | Anthropic | 2002 ± 24 | 42 |
| 24 | Claude Opus 4.8 (High) | Anthropic | 1999 ± 38 | 18 |
| 25 | GPT-5.4 (xHigh) | OpenAI | 1997 ± 21 | 95 |
| 26 | GPT-5.5 (Medium) | OpenAI | 1997 ± 34 | 39 |
| 27 | Gemini 3.1 Pro (Preview) (High) | 1986 ± 37 | 40 | |
| 28 | Kimi K3 | Moonshot | 1985 ± 20 | 93 |
| 29 | GPT-5.6 Luna (Max) | OpenAI | 1984 ± 27 | 30 |
| 30 | Claude Opus 4.8 (xHigh) | Anthropic | 1984 ± 26 | 12 |
| 31 | GPT-5.6 Terra (xHigh) | OpenAI | 1979 ± 34 | 27 |
| 32 | GPT-5.6 Sol | OpenAI | 1978 ± 22 | 108 |
| 33 | GPT-5.2 (High) | OpenAI | 1978 ± 25 | 99 |
| 34 | Gemini 3.6 Flash | 1974 ± 58 | 26 | |
| 35 | Claude Sonnet 4.5 (High) | Anthropic | 1973 ± 34 | 25 |
| 36 | Claude Sonnet 5 (High) | Anthropic | 1970 ± 24 | 14 |
| 37 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | Anthropic | 1965 ± 36 | 20 |
| 38 | Claude Opus 4.7 (xHigh) | Anthropic | 1963 ± 65 | 24 |
| 39 | Gemini 3 Pro (Preview) (High) | 1952 ± 27 | 30 | |
| 40 | GPT-5.6 Sol (Low) | OpenAI | 1952 ± 26 | 22 |
| 41 | Claude Opus 4.6 (Thinking) | Anthropic | 1944 ± 19 | 133 |
| 42 | GPT-5.6 Terra (High) | OpenAI | 1944 ± 32 | 26 |
| 43 | Claude Sonnet 4.6 (Max) | Anthropic | 1944 ± 40 | 15 |
| 44 | Gemini 3.5 Flash (Medium) | 1942 ± 23 | 29 | |
| 45 | Claude Opus 4.7 (Adaptive Reasoning, Max Effort) | Anthropic | 1936 ± 35 | 20 |
| 46 | Gemini 3.1 Pro (Preview) (Low) | 1936 ± 57 | 7 | |
| 47 | Grok 4.5 (High) | xAI | 1931 ± 21 | 32 |
| 48 | GPT-5.4 (Medium) | OpenAI | 1930 ± 28 | 26 |
| 49 | GPT-5.3 Codex (xHigh) | OpenAI | 1929 ± 28 | 26 |
| 50 | Gemini 3.5 Flash (High) | 1928 ± 24 | 57 | |
| 51 | GPT-5.2 Pro | OpenAI | 1926 ± 27 | 49 |
| 52 | GLM-5.2 (Max) | Zhipu | 1925 ± 25 | 45 |
| 53 | Claude Opus 4.8 (Thinking) | Anthropic | 1916 ± 26 | 15 |
| 54 | GPT-5.4 (High) | OpenAI | 1915 ± 23 | 68 |
| 55 | Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | Anthropic | 1915 ± 41 | 17 |
| 56 | O3 Pro (High) | OpenAI | 1914 ± 95 | 8 |
| 57 | Claude Sonnet 5 (xHigh) | Anthropic | 1908 ± 39 | 8 |
| 58 | GPT-5.5 | OpenAI | 1907 ± 10 | 630 |
| 59 | GPT-5.6 Terra (Medium) | OpenAI | 1907 ± 28 | 23 |
| 60 | Qwen 3.7 Max (Max) | Alibaba | 1907 ± 40 | 20 |
| 61 | Gemini 3.1 Pro (Preview) (Thinking) | 1907 ± 30 | 13 | |
| 62 | GPT-5.5 (Low) | OpenAI | 1904 ± 23 | 29 |
| 63 | Claude Opus 4.8 | Anthropic | 1901 ± 9 | 440 |
| 64 | GPT-5.6 Luna (xHigh) | OpenAI | 1901 ± 30 | 24 |
| 65 | GPT-5.6 Luna (High) | OpenAI | 1900 ± 23 | 24 |
| 66 | GPT-5.2 (Medium) | OpenAI | 1899 ± 20 | 123 |
| 67 | Claude Opus 4.7 | Anthropic | 1893 ± 9 | 589 |
| 68 | Gemini 3.1 Pro (Preview) | 1890 ± 9 | 779 | |
| 69 | Claude Sonnet 5 | Anthropic | 1890 ± 16 | 96 |
| 70 | Claude Opus 4.7 (Thinking) | Anthropic | 1889 ± 25 | 25 |
| 71 | Gemini 3.5 Flash | 1887 ± 14 | 175 | |
| 72 | Muse Spark 1.1 | Meta | 1886 ± 18 | 63 |
| 73 | Claude Sonnet 4.6 (Thinking) | Anthropic | 1884 ± 51 | 24 |
| 74 | plutus-8B-instruct | Other | 1884 ± 106 | 8 |
| 75 | GPT-5.4 (Thinking) | OpenAI | 1883 ± 31 | 8 |
| 76 | Claude Opus 4.6 (Thinking, High) | Anthropic | 1883 ± 39 | 8 |
| 77 | Grok 4.5 | xAI | 1882 ± 17 | 77 |
| 78 | GPT-5.2 Codex (xHigh) | OpenAI | 1882 ± 29 | 19 |
| 79 | GPT-5.6 Terra | OpenAI | 1879 ± 16 | 90 |
| 80 | GPT-5 Pro | OpenAI | 1879 ± 32 | 28 |
| 81 | GPT-5.3 Codex (High) | OpenAI | 1879 ± 17 | 12 |
| 82 | Claude Opus 4.6 (Adaptive Reasoning, Max Effort) | Anthropic | 1878 ± 26 | 29 |
| 83 | GPT-5.2 Codex (High) | OpenAI | 1877 ± 11 | 7 |
| 84 | DeepSeek V4 Pro (Max) | DeepSeek | 1873 ± 21 | 46 |
| 85 | Claude Opus 4.6 (Max) | Anthropic | 1873 ± 31 | 43 |
| 86 | Muse Spark | Meta | 1871 ± 16 | 79 |
| 87 | DeepSeek V4 Flash (Max) | DeepSeek | 1871 ± 23 | 32 |
| 88 | Gemini 3.1 Flash | 1871 ± 77 | 13 | |
| 89 | Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) | Anthropic | 1868 ± 20 | 25 |
| 90 | Gemini 3 Flash (Preview) (Medium) | 1868 ± 50 | 8 | |
| 91 | GPT-5.6 Luna | OpenAI | 1864 ± 15 | 88 |
| 92 | Claude Opus 4.6 | Anthropic | 1862 ± 12 | 430 |
| 93 | Nex N2 Pro | Nex AGI | 1862 ± 27 | 25 |
| 94 | GPT-5.6 Sol (Non-reasoning) | OpenAI | 1862 ± 31 | 16 |
| 95 | Claude Opus 4.6 (Thinking 32K) | Anthropic | 1862 ± 74 | 7 |
| 96 | Claude Opus 4.6 (High) | Anthropic | 1860 ± 27 | 30 |
| 97 | Gemini 3 Flash (Preview) (High) | 1860 ± 31 | 24 | |
| 98 | Claude Opus 4.5 (20251101) (Unknown) | Anthropic | 1860 ± 22 | 7 |
| 99 | Gemini 3 Flash (Preview) | 1856 ± 16 | 238 | |
| 100 | Claude Opus 4.7 (High) | Anthropic | 1856 ± 23 | 31 |
Interactive version: theaggregate.ai/models · How the rankings work · Data refreshed daily, snapshot 2026-07-22.