AI Model Leaderboard — Elo Rankings (2026)
claude-opus-5-high from anthropic is the #1 ranked AI model with an Elo score of 1504.20, leading a field of 100 models. Rankings are sourced from LMArena (Chatbot Arena) via Hugging Face as of 2026-08-23. See the full ranked table below.
Source: LMArena (Chatbot Arena) via Hugging Face · as of 2026-08-23
| Rank | Model | Score | Votes | Org |
|---|---|---|---|---|
| 1 | claude-opus-5-high | 1504.20 | 27,610 | anthropic |
| 2 | claude-opus-5-max | 1504.04 | 13,403 | anthropic |
| 3 | claude-opus-4-6-high | 1502.68 | 72,359 | anthropic |
| 4 | claude-opus-4-6 | 1497.20 | 76,362 | anthropic |
| 5 | claude-fable-5 | 1494.68 | 24,331 | anthropic |
| 6 | gemini-3.7-flash-high | 1490.21 | 5,718 | |
| 7 | claude-opus-4-7-high | 1490.12 | 60,203 | anthropic |
| 8 | muse-spark-1.2 (xHigh) | 1487.37 | 3,257 | meta |
| 9 | claude-opus-4-7 | 1482.74 | 61,304 | anthropic |
| 10 | gemini-3.5-flash-high | 1482.63 | 30,004 | |
| 11 | qwen3.8-max | 1481.89 | 9,955 | alibaba |
| 12 | gemini-3.1-pro-preview | 1479.55 | 99,182 | |
| 13 | gemini-3-pro | 1479.35 | 41,491 | |
| 14 | muse-spark-1.1 | 1478.32 | 20,242 | meta |
| 15 | glm-5.3-max | 1476.93 | 3,751 | zai |
| 16 | gemini-3.6-flash-high | 1476.48 | 18,018 | |
| 17 | kimi-k3-max | 1476.29 | 15,054 | moonshot |
| 18 | gemini-3.5-flash-medium | 1475.21 | 28,343 | |
| 19 | qwen3.7-max-preview | 1474.30 | 3,712 | alibaba |
| 20 | muse-spark | 1473.53 | 13,584 | meta |
| 21 | qwen3.5-max-preview | 1470.92 | 21,484 | alibaba |
| 22 | gpt-5.5-high | 1470.88 | 59,545 | openai |
| 23 | gpt-5.4-high | 1469.57 | 60,708 | openai |
| 24 | ernie-5.1 | 1468.08 | 37,137 | baidu |
| 25 | gemini-3-flash | 1465.97 | 30,852 | |
| 26 | gpt-5.5 | 1465.80 | 60,896 | openai |
| 27 | glm-5.2-max | 1465.38 | 30,637 | zai |
| 28 | mimo-v2.5-pro | 1464.97 | 54,177 | xiaomi |
| 29 | glm-5.1 | 1464.11 | 42,267 | zai |
| 30 | claude-opus-4-8-high | 1460.91 | 44,676 | anthropic |
| 31 | claude-sonnet-4-6 | 1457.57 | 66,512 | anthropic |
| 32 | gemini-2.5-pro | 1457.34 | 124,807 | |
| 33 | qwen3.7-plus | 1456.24 | 34,426 | alibaba |
| 34 | kimi-k2.6 | 1455.02 | 37,543 | moonshot |
| 35 | gpt-5.6-sol-xhigh | 1454.17 | 19,541 | openai |
| 36 | gpt-5.4 | 1452.59 | 63,659 | openai |
| 37 | grok-4.5 | 1452.30 | 22,030 | xai |
| 38 | claude-opus-4-8 | 1451.95 | 45,331 | anthropic |
| 39 | grok-4.20-beta-0309-reasoning | 1450.88 | 62,272 | xai |
| 40 | deepseek-v4-pro | 1450.87 | 54,263 | deepseek |
| 41 | grok-4.20-multi-agent-beta-0309 | 1449.90 | 60,864 | xai |
| 42 | claude-opus-4-5-20251101 | 1449.85 | 70,985 | anthropic |
| 43 | dola-seed-2.0-pro | 1447.85 | 74,513 | bytedance |
| 44 | amazon-nova-experimental-chat-26-02-10 | 1447.33 | 3,409 | amazon |
| 45 | claude-opus-4-5-20251101-high-32k | 1446.70 | 37,198 | anthropic |
| 46 | qwen3.6-max-preview | 1446.27 | 5,196 | alibaba |
| 47 | gpt-5.6-terra-xhigh | 1446.03 | 20,216 | openai |
| 48 | glm-5 | 1445.24 | 27,850 | zai |
| 49 | kimi-k2.5-thinking | 1445.23 | 70,943 | moonshot |
| 50 | deepseek-v4-pro-high-preview | 1445.00 | 51,642 | deepseek |
| 51 | nvidia-nemotron-3-ultra-550b-a55b-nvfp4 | 1444.95 | 10,700 | nvidia |
| 52 | ernie-5.0-0110 | 1444.47 | 35,267 | baidu |
| 53 | grok-4.20-beta1 | 1444.43 | 26,770 | xai |
| 54 | grok-4.6-high | 1443.73 | 3,473 | xai |
| 55 | ernie-5.0-preview-1203 | 1442.40 | 9,774 | baidu |
| 56 | gemini-3-flash (thinking-minimal) | 1442.29 | 86,359 | |
| 57 | claude-sonnet-5-high | 1442.25 | 27,366 | anthropic |
| 58 | gemma-4-31b | 1441.70 | 5,899 | |
| 59 | gpt-5.1-high | 1441.37 | 40,945 | openai |
| 60 | hy3 | 1441.17 | 5,877 | tencent |
| 61 | qwen3.8-27b | 1440.77 | 3,205 | alibaba |
| 62 | glm-4.6 | 1439.77 | 35,830 | zai |
| 63 | inkling | 1439.24 | 18,488 | thinky |
| 64 | deepseek-v4-pro-high-20260813 | 1439.16 | 3,621 | deepseek |
| 65 | qwen3-max-preview | 1439.07 | 27,838 | alibaba |
| 66 | gpt-5.2-chat-latest-20260210 | 1438.89 | 34,339 | openai |
| 67 | qwen3.5-397b-a17b | 1438.25 | 70,207 | alibaba |
| 68 | claude-sonnet-4-5-20250929 | 1437.98 | 80,858 | anthropic |
| 69 | grok-4.1-thinking | 1437.11 | 65,550 | xai |
| 70 | qwen3.6-plus | 1436.83 | 45,376 | alibaba |
| 71 | glm-5v-turbo | 1436.80 | 9,380 | zai |
| 72 | mimo-v2-pro | 1436.53 | 24,397 | xiaomi |
| 73 | gemini-3.5-flash-lite | 1436.48 | 17,985 | |
| 74 | grok-4.1 | 1436.43 | 67,767 | xai |
| 75 | glm-4.7 | 1435.34 | 12,155 | zai |
| 76 | minimax-m3 | 1434.76 | 41,023 | minimax |
| 77 | gemma-4-26b-a4b | 1434.62 | 5,809 | |
| 78 | claude-sonnet-4-5-20250929-high-32k | 1433.33 | 82,473 | anthropic |
| 79 | deepseek-v4-flash | 1431.61 | 49,001 | deepseek |
| 80 | glm-4.5 | 1429.42 | 24,403 | zai |
| 81 | ernie-5.0-preview-1022 | 1429.10 | 4,737 | baidu |
| 82 | chatgpt-4o-latest-20250326 | 1428.58 | 82,766 | openai |
| 83 | gpt-5.6-luna-xhigh | 1428.54 | 20,693 | openai |
| 84 | mistral-large-3 | 1428.31 | 62,644 | mistral |
| 85 | deepseek-r1-0528 | 1427.91 | 18,492 | deepseek |
| 86 | mimo-v2.5 | 1427.33 | 44,557 | xiaomi |
| 87 | longcat-flash-chat-2602-exp | 1425.76 | 27,982 | meituan |
| 88 | grok-3-preview-02-24 | 1425.11 | 32,941 | xai |
| 89 | mistral-medium-2508 | 1425.05 | 94,016 | mistral |
| 90 | deepseek-v3.2 | 1424.62 | 47,295 | deepseek |
| 91 | deepseek-v3.2-exp-thinking | 1424.38 | 9,109 | deepseek |
| 92 | deepseek-v4-flash-high-preview | 1423.97 | 48,679 | deepseek |
| 93 | deepseek-v3.2-exp | 1422.55 | 11,982 | deepseek |
| 94 | mimo-v2-omni | 1422.26 | 19,434 | xiaomi |
| 95 | gpt-5.1 | 1422.22 | 43,653 | openai |
| 96 | longcat-flash-chat | 1422.22 | 11,426 | meituan |
| 97 | mistral-medium-3.5 | 1420.88 | 11,009 | mistral |
| 98 | qwen3-vl-235b-a22b-instruct | 1420.86 | 11,556 | alibaba |
| 99 | kimi-k2.5-instant | 1420.35 | 8,186 | moonshot |
| 100 | amazon-nova-experimental-chat-12-10 | 1419.88 | 3,703 | amazon |
Generate an optimized prompt for any of these models with Prompeteer →