GPT-4.5-preview (2025-02-27)* |
0.929 |
0.940 |
0.917 |
0.928 |
1788 |
Athene-V2 (72B-L) |
0.925 |
0.932 |
0.917 |
0.925 |
1741 |
Qwen 2.5 (72B-L) |
0.924 |
0.932 |
0.915 |
0.923 |
1728 |
GPT-4o (2024-05-13) |
0.921 |
0.905 |
0.941 |
0.923 |
1725 |
GPT-4o (2024-11-20) |
0.921 |
0.922 |
0.920 |
0.921 |
1722 |
GPT-4 (0613) |
0.920 |
0.927 |
0.912 |
0.919 |
1687 |
Grok Beta |
0.916 |
0.906 |
0.928 |
0.917 |
1685 |
Pixtral Large (2411) |
0.913 |
0.884 |
0.952 |
0.917 |
1683 |
OpenThinker (32B-L) |
0.916 |
0.915 |
0.917 |
0.916 |
1681 |
Qwen 2.5 (14B-L) |
0.915 |
0.904 |
0.928 |
0.916 |
1680 |
GPT-4 Turbo (2024-04-09) |
0.912 |
0.880 |
0.955 |
0.916 |
1679 |
GPT-4o (2024-08-06) |
0.913 |
0.895 |
0.936 |
0.915 |
1666 |
Qwen 2.5 (32B-L) |
0.915 |
0.919 |
0.909 |
0.914 |
1665 |
Gemini 2.0 Flash |
0.909 |
0.872 |
0.960 |
0.914 |
1664 |
Llama 3.1 (70B-L) |
0.912 |
0.908 |
0.917 |
0.912 |
1664 |
o1 (2024-12-17) |
0.911 |
0.895 |
0.931 |
0.912 |
1663 |
Nous Hermes 2 (11B-L) |
0.912 |
0.912 |
0.912 |
0.912 |
1663 |
Gemini 1.5 Flash |
0.909 |
0.889 |
0.936 |
0.912 |
1663 |
Grok 2 (1212) |
0.900 |
0.864 |
0.949 |
0.905 |
1658 |
Gemini 1.5 Flash (8B) |
0.905 |
0.909 |
0.901 |
0.905 |
1658 |
Gemini 1.5 Pro |
0.900 |
0.859 |
0.957 |
0.905 |
1657 |
Falcon3 (10B-L) |
0.904 |
0.891 |
0.920 |
0.906 |
1656 |
Exaone 3.5 (32B-L) |
0.907 |
0.913 |
0.899 |
0.906 |
1656 |
Aya (35B-L) |
0.908 |
0.925 |
0.888 |
0.906 |
1655 |
Gemini 2.0 Flash-Lite (02-05) |
0.903 |
0.872 |
0.944 |
0.907 |
1655 |
Gemma 2 (27B-L) |
0.905 |
0.892 |
0.923 |
0.907 |
1654 |
Llama 3.3 (70B-L) |
0.904 |
0.880 |
0.936 |
0.907 |
1653 |
Llama 3.1 (405B) |
0.904 |
0.880 |
0.936 |
0.907 |
1653 |
Aya Expanse (32B-L) |
0.905 |
0.888 |
0.928 |
0.907 |
1652 |
Open Mixtral 8x22B |
0.911 |
0.935 |
0.883 |
0.908 |
1652 |
Aya Expanse (8B-L) |
0.905 |
0.876 |
0.944 |
0.909 |
1651 |
GLM-4 (9B-L) |
0.911 |
0.925 |
0.893 |
0.909 |
1651 |
Nemotron (70B-L) |
0.908 |
0.896 |
0.923 |
0.909 |
1650 |
DeepSeek-R1 (671B) |
0.905 |
0.869 |
0.955 |
0.910 |
1650 |
Sailor2 (20B-L) |
0.912 |
0.933 |
0.888 |
0.910 |
1650 |
Gemma 3 (27B-L)* |
0.904 |
0.865 |
0.957 |
0.909 |
1650 |
DeepSeek-V3 (671B) |
0.913 |
0.948 |
0.875 |
0.910 |
1650 |
GPT-4o mini (2024-07-18) |
0.908 |
0.884 |
0.939 |
0.911 |
1649 |
Phi-4 (14B-L) |
0.901 |
0.899 |
0.904 |
0.902 |
1645 |
Qwen 2.5 (7B-L) |
0.900 |
0.887 |
0.917 |
0.902 |
1644 |
Hermes 3 (70B-L) |
0.905 |
0.937 |
0.869 |
0.902 |
1643 |
Gemma 3 (12B-L)* |
0.899 |
0.866 |
0.944 |
0.903 |
1642 |
Mistral Large (2411) |
0.896 |
0.863 |
0.941 |
0.901 |
1629 |
o1-preview (2024-09-12)+ |
0.800 |
0.731 |
0.991 |
0.841 |
1622 |
o3-mini (2025-01-31) |
0.896 |
0.886 |
0.909 |
0.897 |
1615 |
DeepSeek-R1 D-Qwen (14B-L) |
0.897 |
0.896 |
0.899 |
0.897 |
1614 |
o1-mini (2024-09-12) |
0.895 |
0.878 |
0.917 |
0.897 |
1599 |
Mistral NeMo (12B-L) |
0.891 |
0.873 |
0.915 |
0.893 |
1586 |
Command R7B Arabic (7B-L)* |
0.897 |
0.926 |
0.864 |
0.894 |
1584 |
GPT-3.5 Turbo (0125) |
0.875 |
0.822 |
0.957 |
0.884 |
1564 |
QwQ (32B-L) |
0.892 |
0.940 |
0.837 |
0.886 |
1562 |
Gemma 2 (9B-L) |
0.876 |
0.818 |
0.968 |
0.886 |
1560 |
Mistral (7B-L) |
0.891 |
0.897 |
0.883 |
0.890 |
1558 |
Llama 3.1 (8B-L) |
0.889 |
0.878 |
0.904 |
0.891 |
1556 |
Marco-o1-CoT (7B-L) |
0.888 |
0.866 |
0.917 |
0.891 |
1554 |
Phi-4-mini (3.8B-L)* |
0.884 |
0.891 |
0.875 |
0.883 |
1553 |
Mistral Small (22B-L) |
0.871 |
0.806 |
0.976 |
0.883 |
1551 |
OpenThinker (7B-L) |
0.872 |
0.812 |
0.968 |
0.883 |
1549 |
Tülu3 (8B-L) |
0.881 |
0.893 |
0.867 |
0.880 |
1541 |
Tülu3 (70B-L) |
0.891 |
0.962 |
0.813 |
0.882 |
1538 |
OLMo 2 (7B-L) |
0.871 |
0.868 |
0.875 |
0.871 |
1527 |
OLMo 2 (13B-L) |
0.867 |
0.804 |
0.971 |
0.879 |
1525 |
Llama 3.2 (3B-L) |
0.876 |
0.885 |
0.864 |
0.874 |
1525 |
Claude 3.5 Haiku (20241022) |
0.885 |
0.947 |
0.816 |
0.877 |
1522 |
Pixtral-12B (2409) |
0.865 |
0.804 |
0.965 |
0.878 |
1519 |
Mistral Saba* |
0.867 |
0.810 |
0.957 |
0.878 |
1516 |
Orca 2 (7B-L) |
0.876 |
0.910 |
0.835 |
0.871 |
1514 |
Claude 3.7 Sonnet (20250219)* |
0.887 |
0.950 |
0.816 |
0.878 |
1513 |
DeepSeek-R1 D-Llama (8B-L) |
0.865 |
0.837 |
0.907 |
0.871 |
1511 |
Claude 3.5 Sonnet (20241022) |
0.887 |
0.950 |
0.816 |
0.878 |
1510 |
Yi 1.5 (9B-L) |
0.859 |
0.826 |
0.909 |
0.865 |
1496 |
Granite 3.1 (8B-L) |
0.869 |
0.921 |
0.808 |
0.861 |
1495 |
Yi Large |
0.871 |
0.979 |
0.757 |
0.854 |
1449 |
Nous Hermes 2 Mixtral (47B-L) |
0.867 |
0.963 |
0.763 |
0.851 |
1438 |
Mistral OpenOrca (7B-L) |
0.863 |
0.939 |
0.776 |
0.850 |
1434 |
Gemma 3 (4B-L)* |
0.820 |
0.742 |
0.981 |
0.845 |
1428 |
Ministral-8B (2410) |
0.823 |
0.744 |
0.984 |
0.847 |
1427 |
Exaone 3.5 (8B-L) |
0.853 |
0.913 |
0.781 |
0.842 |
1416 |
Codestral Mamba (7B) |
0.827 |
0.774 |
0.923 |
0.842 |
1415 |
Dolphin 3.0 (8B-L) |
0.807 |
0.731 |
0.971 |
0.834 |
1386 |
Granite 3.2 (8B-L)* |
0.849 |
0.940 |
0.747 |
0.832 |
1359 |
Yi 1.5 (34B-L) |
0.849 |
0.955 |
0.733 |
0.830 |
1333 |
Solar Pro (22B-L) |
0.844 |
0.916 |
0.757 |
0.829 |
1304 |
Hermes 3 (8B-L) |
0.840 |
0.932 |
0.733 |
0.821 |
1244 |
DeepSeek-R1 D-Qwen (7B-L) |
0.821 |
0.832 |
0.805 |
0.818 |
1228 |
Nemotron-Mini (4B-L) |
0.771 |
0.696 |
0.963 |
0.808 |
1197 |
Phi-3 Medium (14B-L) |
0.815 |
0.940 |
0.672 |
0.784 |
1089 |
Yi 1.5 (6B-L) |
0.807 |
0.908 |
0.683 |
0.779 |
1056 |
DeepScaleR (1.5B-L)* |
0.620 |
0.688 |
0.440 |
0.537 |
891 |
Perspective 0.55 |
0.768 |
0.986 |
0.544 |
0.701 |
880 |
Granite 3 MoE (3B-L) |
0.747 |
0.894 |
0.560 |
0.689 |
877 |
DeepSeek-R1 D-Qwen (1.5B-L) |
0.633 |
0.685 |
0.493 |
0.574 |
800 |
Perspective 0.60 |
0.731 |
0.989 |
0.467 |
0.634 |
778 |
Perspective 0.70 |
0.665 |
1.000 |
0.331 |
0.497 |
747 |
Perspective 0.80 |
0.609 |
1.000 |
0.219 |
0.359 |
665 |
Granite 3.1 MoE (3B-L) |
0.555 |
1.000 |
0.109 |
0.197 |
577 |