AI Model Leaderboard — Elo Rankings (2026)
claude-opus-4-6-thinking from anthropic is the #1 ranked AI model with an Elo score of 1501.18, leading a field of 100 models. Rankings are sourced from LMArena (Chatbot Arena) via Hugging Face as of 2026-07-11. See the full ranked table below.
Source: LMArena (Chatbot Arena) via Hugging Face · as of 2026-07-11
| Rank | Model | Score | Votes | Org |
|---|---|---|---|---|
| 1 | claude-opus-4-6-thinking | 1501.18 | 58,968 | anthropic |
| 2 | claude-opus-4-6 | 1497.51 | 62,650 | anthropic |
| 3 | claude-fable-5 | 1495.08 | 4,299 | anthropic |
| 4 | claude-opus-4-7-thinking | 1490.15 | 46,183 | anthropic |
| 5 | claude-opus-4-7 | 1482.45 | 47,222 | anthropic |
| 6 | gemini-3.5-flash-high | 1480.08 | 10,110 | |
| 7 | gemini-3-pro | 1479.50 | 41,308 | |
| 8 | gemini-3.1-pro-preview | 1479.00 | 78,561 | |
| 9 | muse-spark-1.1 | 1477.86 | 3,750 | meta |
| 10 | gemini-3.5-flash-medium | 1476.78 | 9,492 | |
| 11 | qwen3.7-max-preview | 1475.38 | 3,719 | alibaba |
| 12 | muse-spark | 1472.74 | 13,573 | meta |
| 13 | qwen3.5-max-preview | 1470.25 | 21,507 | alibaba |
| 14 | gpt-5.5-high | 1468.63 | 41,341 | openai |
| 15 | gpt-5.4-high | 1468.48 | 54,566 | openai |
| 16 | glm-5.1 | 1467.45 | 26,549 | zai |
| 17 | ernie-5.1 | 1467.26 | 36,321 | baidu |
| 18 | gemini-3-flash | 1466.30 | 30,712 | |
| 19 | gpt-5.5 | 1463.08 | 42,644 | openai |
| 20 | mimo-v2.5-pro | 1462.38 | 38,175 | xiaomi |
| 21 | claude-opus-4-8-thinking | 1460.69 | 26,557 | anthropic |
| 22 | glm-5.2 (max) | 1460.47 | 13,442 | zai |
| 23 | qwen3.7-plus | 1458.55 | 18,501 | alibaba |
| 24 | gpt-5.6-sol-xhigh | 1457.84 | 1,740 | openai |
| 25 | gemini-2.5-pro | 1457.36 | 124,468 | |
| 26 | claude-sonnet-4-6 | 1457.13 | 52,860 | anthropic |
| 27 | kimi-k2.6 | 1455.61 | 35,917 | moonshot |
| 28 | grok-4.5 | 1455.01 | 3,224 | xai |
| 29 | claude-opus-4-8 | 1452.83 | 26,957 | anthropic |
| 30 | grok-4.20-beta-0309-reasoning | 1452.83 | 55,900 | xai |
| 31 | gpt-5.4 | 1451.88 | 57,271 | openai |
| 32 | grok-4.20-multi-agent-beta-0309 | 1449.88 | 54,737 | xai |
| 33 | claude-opus-4-5-20251101 | 1449.46 | 71,066 | anthropic |
| 34 | deepseek-v4-pro | 1449.25 | 41,017 | deepseek |
| 35 | amazon-nova-experimental-chat-26-02-10 | 1448.26 | 3,421 | amazon |
| 36 | dola-seed-2.0-pro | 1447.48 | 63,499 | bytedance |
| 37 | deepseek-v4-pro-thinking | 1446.72 | 39,019 | deepseek |
| 38 | claude-opus-4-5-20251101-thinking-32k | 1446.61 | 37,064 | anthropic |
| 39 | qwen3.6-max-preview | 1446.43 | 5,210 | alibaba |
| 40 | ernie-5.0-0110 | 1445.08 | 35,255 | baidu |
| 41 | glm-5 | 1445.00 | 27,818 | zai |
| 42 | kimi-k2.5-thinking | 1444.43 | 59,062 | moonshot |
| 43 | grok-4.20-beta1 | 1444.31 | 26,883 | xai |
| 44 | gemini-3-flash (thinking-minimal) | 1444.17 | 79,866 | |
| 45 | glm-5v-turbo | 1443.28 | 3,358 | zai |
| 46 | claude-sonnet-5-high | 1442.91 | 9,008 | anthropic |
| 47 | ernie-5.0-preview-1203 | 1442.23 | 9,743 | baidu |
| 48 | gemma-4-31b | 1441.53 | 5,884 | |
| 49 | gpt-5.1-high | 1441.16 | 40,815 | openai |
| 50 | nvidia-nemotron-3-ultra-550b-a55b-nvfp4 | 1440.69 | 9,406 | nvidia |
| 51 | glm-4.6 | 1440.47 | 35,625 | zai |
| 52 | qwen3-max-preview | 1439.04 | 27,707 | alibaba |
| 53 | gpt-5.2-chat-latest-20260210 | 1438.32 | 34,462 | openai |
| 54 | qwen3.5-397b-a17b | 1438.25 | 54,262 | alibaba |
| 55 | claude-sonnet-4-5-20250929 | 1437.77 | 80,788 | anthropic |
| 56 | grok-4.1-thinking | 1437.45 | 65,529 | xai |
| 57 | minimax-m3 | 1437.14 | 23,823 | minimax |
| 58 | grok-4.1 | 1436.58 | 67,666 | xai |
| 59 | qwen3.6-plus | 1436.30 | 40,143 | alibaba |
| 60 | glm-4.7 | 1436.13 | 12,103 | zai |
| 61 | mimo-v2-pro | 1436.08 | 24,530 | xiaomi |
| 62 | gemma-4-26b-a4b | 1434.37 | 5,806 | |
| 63 | deepseek-v4-flash | 1433.25 | 40,831 | deepseek |
| 64 | claude-sonnet-4-5-20250929-thinking-32k | 1432.75 | 82,391 | anthropic |
| 65 | mistral-large-3 | 1430.60 | 47,096 | mistral |
| 66 | ernie-5.0-preview-1022 | 1429.81 | 4,704 | baidu |
| 67 | glm-4.5 | 1428.98 | 24,288 | zai |
| 68 | chatgpt-4o-latest-20250326 | 1428.88 | 82,415 | openai |
| 69 | deepseek-r1-0528 | 1428.00 | 18,452 | deepseek |
| 70 | mimo-v2.5 | 1427.18 | 39,076 | xiaomi |
| 71 | longcat-flash-chat-2602-exp | 1425.52 | 28,117 | meituan |
| 72 | mistral-medium-2508 | 1425.36 | 93,892 | mistral |
| 73 | grok-3-preview-02-24 | 1425.01 | 32,901 | xai |
| 74 | deepseek-v3.2 | 1424.49 | 47,243 | deepseek |
| 75 | deepseek-v4-flash-thinking | 1424.13 | 40,631 | deepseek |
| 76 | deepseek-v3.2-exp-thinking | 1424.04 | 9,066 | deepseek |
| 77 | deepseek-v3.2-exp | 1422.66 | 11,921 | deepseek |
| 78 | longcat-flash-chat | 1422.19 | 11,385 | meituan |
| 79 | gpt-5.1 | 1422.06 | 43,434 | openai |
| 80 | mimo-v2-omni | 1421.91 | 19,533 | xiaomi |
| 81 | qwen3-vl-235b-a22b-instruct | 1421.39 | 11,499 | alibaba |
| 82 | mistral-medium-3.5 | 1420.83 | 11,052 | mistral |
| 83 | kimi-k2.5-instant | 1420.67 | 8,179 | moonshot |
| 84 | deepseek-v3.2-thinking | 1420.13 | 41,035 | deepseek |
| 85 | deepseek-v3.1-terminus-thinking | 1420.06 | 3,458 | deepseek |
| 86 | amazon-nova-experimental-chat-12-10 | 1419.85 | 3,678 | amazon |
| 87 | qwen3-235b-a22b-instruct-2507 | 1419.45 | 97,160 | alibaba |
| 88 | gpt-5.5-instant | 1419.42 | 26,138 | openai |
| 89 | deepseek-v3.1 | 1419.42 | 14,945 | deepseek |
| 90 | qwen3-next-80b-a3b-instruct | 1418.76 | 22,855 | alibaba |
| 91 | claude-opus-4-1-20250805-thinking-16k | 1418.43 | 49,772 | anthropic |
| 92 | qwen3.5-122b-a10b | 1417.85 | 28,517 | alibaba |
| 93 | claude-opus-4-1-20250805 | 1417.50 | 77,272 | anthropic |
| 94 | gpt-4.5-preview-2025-02-27 | 1417.47 | 14,547 | openai |
| 95 | deepseek-v3.1-terminus | 1417.41 | 3,692 | deepseek |
| 96 | gemini-2.5-flash | 1417.38 | 124,403 | |
| 97 | deepseek-v3.1-thinking | 1417.09 | 11,728 | deepseek |
| 98 | amazon-nova-experimental-chat-11-10 | 1416.43 | 25,358 | amazon |
| 99 | gpt-5.2-high | 1416.09 | 48,012 | openai |
| 100 | gemini-3.1-flash-lite-preview | 1414.52 | 60,963 |
Generate an optimized prompt for any of these models with Prompeteer →