---
title: "Text: model rankings and source evidence · Undominated.ai"
canonical: https://undominated.ai/rankings/arena-text/
description: "Text ranked by Arena score. Inspect exact model variants, source dates, measurement limits and downloadable evidence."
---

# Text: model rankings and source evidence · Undominated.ai

> Text ranked by Arena score. Inspect exact model variants, source dates, measurement limits and downloadable evidence.

[All rankings](/rankings/) / Language models

# Text

Human preference ratings for the overall category of this Arena task. Scores from different boards are not interchangeable.

**419 entries** · Arena score · Higher is better

Source publication: 2026-10-28. Retrieved 2026-11-05.

Source: [Arena (lmarena-ai)](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset) · [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/).

Ranks use confidence bounds. Several models can share a rank; the rows within a shared rank are displayed by score.

Text · Arena score

| Significance rank | Model / evaluated variant | Arena score | 95% confidence interval | Votes |
| --- | --- | --- | --- | --- |
| 1 | Gemini 4 Carbon (High) google | 1,540.04 | 1,530.69 – 1,549.4 | 4,403 |
| 1 | Gemini 4 Argon (High) google | 1,528.58 | 1,522.35 – 1,534.81 | 11,889 |
| 2 | Claude Opus 5.5 (High) anthropic | 1,515.8 | 1,509.2 – 1,522.4 | 11,415 |
| 3 | Claude Fable 5.1 (Max) anthropic | 1,513.83 | 1,508.03 – 1,519.64 | 17,178 |
| 3 | Claude Opus 5 (Max) anthropic | 1,507.91 | 1,503.25 – 1,512.57 | 35,531 |
| 5 | Claude Opus 5 (High) anthropic | 1,504.08 | 1,500.52 – 1,507.65 | 73,167 |
| 5 | Claude Opus 4.6 (High) anthropic | 1,501.72 | 1,498.48 – 1,504.97 | 84,512 |
| 5 | Muse Wonder (Max) meta | 1,499.17 | 1,491.87 – 1,506.46 | 7,749 |
| 6 | Gemini 3.8 Flash (High) google | 1,498.49 | 1,494.06 – 1,502.92 | 47,803 |
| 7 | Claude Opus 4.6 anthropic | 1,496.25 | 1,493.09 – 1,499.41 | 89,324 |
| 8 | Claude Fable 5 (High) anthropic | 1,491.56 | 1,487.38 – 1,495.74 | 45,341 |
| 6 | MiMo-V2.6-Pro xiaomi | 1,491.35 | 1,481.97 – 1,500.74 | 4,037 |
| 8 | Muse Spark 1.3 (Max) meta | 1,490.63 | 1,485.41 – 1,495.84 | 22,134 |
| 9 | Claude Opus 4.7 (High) anthropic | 1,489.72 | 1,485.98 – 1,493.46 | 65,110 |
| 9 | Gemini 3.7 Flash (High) google | 1,489.12 | 1,484.46 – 1,493.78 | 32,289 |
| 11 | Qwen3.8-Max alibaba | 1,483.29 | 1,478.52 – 1,488.06 | 31,915 |
| 12 | Claude Opus 4.7 anthropic | 1,482.99 | 1,479.24 – 1,486.74 | 66,140 |
| 11 | Muse Spark 1.2 (xHigh) meta | 1,482.66 | 1,476.33 – 1,489 | 11,724 |
| 12 | Gemini 3.5 Flash (High) google | 1,482.18 | 1,478.31 – 1,486.04 | 48,376 |
| 15 | Gemini 3.1 Pro Preview google | 1,480.11 | 1,477.2 – 1,483.01 | 132,547 |
| 15 | Gemini 3.6 Flash (High) google | 1,479.79 | 1,475.4 – 1,484.19 | 36,028 |
| 15 | Gemini 3 Pro google | 1,479.4 | 1,475.64 – 1,483.16 | 42,057 |
| 15 | Muse Spark 1.1 meta | 1,478.28 | 1,474.16 – 1,482.4 | 46,354 |
| 15 | Gemini 3.5 Flash (Medium) google | 1,478.16 | 1,474.04 – 1,482.28 | 47,196 |
| 16 | Kimi K3 (Max) moonshot | 1,475.69 | 1,471.25 – 1,480.12 | 36,780 |
| 15 | Qwen3.7-Max-Preview alibaba | 1,474.67 | 1,464.99 – 1,484.34 | 3,932 |
| 16 | Muse Spark meta | 1,474.04 | 1,468.33 – 1,479.74 | 14,140 |
| 17 | GLM-5.3 (Max) zai | 1,473.78 | 1,468.85 – 1,478.7 | 26,606 |
| 19 | GLM-5.3-Flash zai | 1,473.04 | 1,468.39 – 1,477.68 | 41,642 |
| 16 | Claude Sonnet 5.5 (xHigh) anthropic | 1,472.85 | 1,466.09 – 1,479.61 | 10,033 |
| 23 | GPT-5.5 (High) openai | 1,471.57 | 1,467.88 – 1,475.26 | 69,377 |
| 23 | Qwen3.5-Max-Preview alibaba | 1,470.39 | 1,465.54 – 1,475.25 | 22,582 |
| 25 | GLM-5.2 (Max) zai | 1,469.64 | 1,465.59 – 1,473.69 | 53,702 |
| 25 | GPT-5.4 (High) openai | 1,469.08 | 1,465.35 – 1,472.81 | 64,748 |
| 25 | ERNIE 5.1 baidu | 1,467.77 | 1,463.26 – 1,472.28 | 39,469 |
| 26 | GPT-5.5 openai | 1,466.75 | 1,463.1 – 1,470.4 | 70,949 |
| 26 | Gemini 3 Flash google | 1,465.67 | 1,461.35 – 1,469.98 | 31,301 |
| 26 | DeepSeek-V4.1-Flash-20260910 (Max) deepseek | 1,464.51 | 1,458.44 – 1,470.58 | 13,657 |
| 30 | MiMo-V2.5-Pro xiaomi | 1,464.22 | 1,460.73 – 1,467.72 | 77,728 |
| 30 | GLM-5.1 zai | 1,462.82 | 1,459.31 – 1,466.32 | 66,771 |
| 34 | Claude Opus 4.8 (High) anthropic | 1,461.3 | 1,457.43 – 1,465.16 | 63,994 |
| 38 | Claude Sonnet 4.6 anthropic | 1,457.71 | 1,454.21 – 1,461.2 | 70,916 |
| 39 | Gemini 2.5 Pro google | 1,457.7 | 1,455.27 – 1,460.14 | 125,307 |
| 37 | GPT-5.6 Sol (xHigh) openai | 1,457.24 | 1,453.01 – 1,461.47 | 43,796 |
| 39 | Kimi K2.6 moonshot | 1,455.56 | 1,451.15 – 1,459.96 | 39,978 |
| 40 | Qwen3.7-Plus alibaba | 1,454.56 | 1,450.24 – 1,458.88 | 42,011 |
| 41 | Claude Opus 4.8 anthropic | 1,454.03 | 1,450.19 – 1,457.88 | 65,121 |
| 42 | GPT-5.4 openai | 1,452.47 | 1,448.82 – 1,456.12 | 67,856 |
| 42 | MiMo-V2.6-Flash xiaomi | 1,451.22 | 1,445.45 – 1,456.98 | 15,312 |
| 43 | DeepSeek-V4-Pro deepseek | 1,451.13 | 1,447.25 – 1,455.01 | 57,572 |
| 43 | Grok 4.20 Beta (Reasoning, 0309) xai | 1,450.98 | 1,447.33 – 1,454.64 | 66,422 |
| 44 | Claude Opus 4.5 (20251101) anthropic | 1,450.9 | 1,447.79 – 1,454 | 72,825 |
| 43 | Grok 4.20 Multi-Agent Beta (0309) xai | 1,450.65 | 1,446.97 – 1,454.33 | 64,917 |
| 41 | amazon-nova-experimental-chat (26-02-10) amazon | 1,448.71 | 1,439.1 – 1,458.33 | 3,523 |
| 45 | GPT-5.6 Terra (xHigh) openai | 1,448.3 | 1,444.18 – 1,452.43 | 48,166 |
| 45 | Claude Opus 4.5 (High, 32K, 20251101) anthropic | 1,448.21 | 1,444.38 – 1,452.04 | 37,484 |
| 45 | Dola Seed 2.0 Pro bytedance | 1,448.03 | 1,444.7 – 1,451.36 | 79,094 |
| 45 | Grok 4.5 xai | 1,447.64 | 1,443.31 – 1,451.97 | 39,801 |
| 43 | Qwen3.6-Max-Preview alibaba | 1,446.74 | 1,438.58 – 1,454.91 | 5,419 |
| 45 | DeepSeek-V4-Pro (High, 20260813) deepseek | 1,446.04 | 1,439.47 – 1,452.61 | 9,787 |
| 48 | GLM-5 zai | 1,445.87 | 1,441.66 – 1,450.09 | 29,255 |
| 45 | GPT-6.1 Sol (Max) openai | 1,445.55 | 1,438.55 – 1,452.56 | 9,367 |
| 45 | NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4) nvidia | 1,445.15 | 1,438.3 – 1,452.01 | 11,563 |
| 48 | DeepSeek-V4-Pro Preview (High) deepseek | 1,444.91 | 1,440.97 – 1,448.85 | 54,870 |
| 49 | Kimi K2.5 (Thinking) moonshot | 1,444.9 | 1,441.65 – 1,448.16 | 74,682 |
| 49 | ERNIE 5.0 (0110) baidu | 1,444.52 | 1,440.66 – 1,448.38 | 36,475 |
| 48 | Grok 4.20 Beta 1 xai | 1,444.48 | 1,439.95 – 1,449.01 | 27,889 |
| 46 | Gemma 4 31B google | 1,442.96 | 1,435.56 – 1,450.36 | 6,138 |
| 48 | Step 5 Preview stepfun | 1,442.72 | 1,436.4 – 1,449.04 | 11,355 |
| 53 | GPT-5.1 (High) openai | 1,442.71 | 1,439.04 – 1,446.39 | 41,639 |
| 53 | Claude Sonnet 5 (High) anthropic | 1,442.69 | 1,438.67 – 1,446.71 | 52,952 |
| 53 | Inkling thinky | 1,442.66 | 1,438.47 – 1,446.85 | 45,472 |
| 53 | Gemini 3 Flash (Minimal) google | 1,442.45 | 1,439.44 – 1,445.46 | 90,997 |
| 49 | ERNIE-5.0-Preview (1203) baidu | 1,442.29 | 1,435.83 – 1,448.75 | 9,802 |
| 52 | GPT-6 Astra (Max) openai | 1,441.15 | 1,435.24 – 1,447.07 | 15,038 |
| 57 | GLM-4.6 zai | 1,440.06 | 1,436.17 – 1,443.94 | 35,810 |
| 54 | Hy3 tencent | 1,439.07 | 1,433.2 – 1,444.93 | 13,840 |
| 57 | Qwen3-Max-Preview alibaba | 1,438.89 | 1,434.39 – 1,443.4 | 27,368 |
| 60 | Claude Sonnet 4.5 (20250929) anthropic | 1,438.51 | 1,435.66 – 1,441.36 | 82,621 |
| 58 | GPT-5.2 Chat (20260210) openai | 1,438.5 | 1,434.5 – 1,442.49 | 35,974 |
| 58 | Qwen3.8-27B alibaba | 1,438.44 | 1,433.61 – 1,443.28 | 27,779 |
| 57 | GLM-5V-Turbo zai | 1,437.72 | 1,431.32 – 1,444.12 | 10,476 |
| 62 | Qwen3.5-397B-A17B alibaba | 1,437.55 | 1,434.52 – 1,440.58 | 97,675 |
| 63 | Grok 4.1 (Thinking) xai | 1,436.41 | 1,433.27 – 1,439.55 | 66,470 |
| 62 | Qwen3.6-Plus alibaba | 1,436.32 | 1,432.21 – 1,440.43 | 48,126 |
| 61 | MiMo-V2-Pro xiaomi | 1,436.08 | 1,431.43 – 1,440.73 | 25,421 |
| 66 | Grok 4.1 xai | 1,435.96 | 1,432.83 – 1,439.08 | 68,599 |
| 63 | Gemini 3.5 Flash-Lite google | 1,435.48 | 1,431.02 – 1,439.94 | 35,740 |
| 60 | GLM-4.7 zai | 1,435.43 | 1,429.41 – 1,441.45 | 12,239 |
| 72 | Claude Sonnet 4.5 (High, 32K, 20250929) anthropic | 1,434.49 | 1,431.73 – 1,437.25 | 83,892 |
| 60 | Gemma 4 26B A4B google | 1,434.17 | 1,426.75 – 1,441.58 | 6,090 |
| 74 | DeepSeek-V4-Flash deepseek | 1,431.83 | 1,427.82 – 1,435.85 | 51,944 |
| 78 | MiniMax-M3 minimax | 1,431.27 | 1,427.55 – 1,434.99 | 68,611 |
| 77 | GPT-5.6 Luna (xHigh) openai | 1,431.05 | 1,426.78 – 1,435.32 | 41,317 |
| 73 | Mistral Large 4 mistral | 1,430.07 | 1,423.88 – 1,436.26 | 12,066 |
| 78 | GLM-4.5 zai | 1,430 | 1,425.11 – 1,434.89 | 23,797 |
| 70 | ERNIE-5.0-Preview (1022) baidu | 1,429.78 | 1,421.02 – 1,438.53 | 4,755 |
| 84 | Grok 4.6 (High) xai | 1,428.53 | 1,423.89 – 1,433.16 | 33,824 |
| 89 | ChatGPT-4o Latest (20250326) openai | 1,428.45 | 1,425.66 – 1,431.24 | 81,893 |
| 89 | Mistral Large 3 mistral | 1,428.28 | 1,425.49 – 1,431.07 | 88,325 |
| 86 | MiMo-V2.5 xiaomi | 1,427.82 | 1,423.61 – 1,432.03 | 47,327 |
| 82 | DeepSeek-R1 (0528) deepseek | 1,427.71 | 1,422.06 – 1,433.37 | 18,165 |
| 89 | LongCat-Flash-Chat Exp (2602) meituan | 1,426.69 | 1,422.21 – 1,431.17 | 29,244 |
| 90 | Grok 3 Preview (02-24) xai | 1,425.42 | 1,421.11 – 1,429.73 | 32,496 |
| 78 | Beam 1.0 501B A23B reflection | 1,425.37 | 1,416.08 – 1,434.66 | 4,233 |
| 87 | DeepSeek-V3.2-Exp (Thinking) deepseek | 1,424.98 | 1,418.43 – 1,431.53 | 8,991 |
| 91 | DeepSeek-V3.2 deepseek | 1,424.43 | 1,420.97 – 1,427.9 | 48,095 |
| 91 | DeepSeek-V4-Flash Preview (High) deepseek | 1,424.31 | 1,420.22 – 1,428.4 | 51,763 |
| 94 | Mistral Medium 3.1 (2508) mistral | 1,424.22 | 1,421.65 – 1,426.78 | 95,269 |
| 91 | MiMo-V2-Omni xiaomi | 1,423.11 | 1,417.59 – 1,428.63 | 20,615 |
| 91 | LongCat-Flash-Chat meituan | 1,422.72 | 1,416.33 – 1,429.11 | 11,167 |
| 95 | GPT-5.1 openai | 1,422.18 | 1,418.63 – 1,425.73 | 44,413 |
| 91 | DeepSeek-V3.2-Exp deepseek | 1,422.16 | 1,415.82 – 1,428.49 | 11,996 |
| 93 | Mistral Medium 3.5 mistral | 1,420.77 | 1,414.4 – 1,427.14 | 11,791 |
| 95 | Kimi K2.5 (Instant) moonshot | 1,420.13 | 1,413.67 – 1,426.59 | 8,371 |
| 95 | Qwen3-VL-235B-A22B-Instruct alibaba | 1,420.04 | 1,413.54 – 1,426.54 | 11,314 |
| 101 | DeepSeek-V3.2 (Thinking) deepseek | 1,419.78 | 1,416.23 – 1,423.34 | 42,033 |
| 96 | DeepSeek-V3.1 deepseek | 1,419.51 | 1,413.47 – 1,425.56 | 14,606 |
| 91 | amazon-nova-experimental-chat (12-10) amazon | 1,419.5 | 1,410.09 – 1,428.92 | 3,734 |
| 101 | Claude Opus 4.1 (Thinking 16K, 20250805) anthropic | 1,419.21 | 1,415.76 – 1,422.67 | 49,535 |
| 98 | GPT-5.5 Instant openai | 1,419.21 | 1,414.28 – 1,424.14 | 27,128 |
| 103 | Qwen3-235B-A22B-Instruct (2507) alibaba | 1,419.17 | 1,416.64 – 1,421.7 | 98,081 |
| 91 | DeepSeek-V3.1-Terminus (Thinking) deepseek | 1,419.14 | 1,409.05 – 1,429.23 | 3,379 |
| 104 | Claude Opus 4.1 (20250805) anthropic | 1,418.56 | 1,415.59 – 1,421.54 | 77,213 |
| 103 | Qwen3.5-122B-A10B alibaba | 1,417.51 | 1,413.25 – 1,421.77 | 29,712 |
| 101 | GPT-4.5 Preview (2025-02-27) openai | 1,417.35 | 1,411.66 – 1,423.03 | 14,547 |
| 93 | DeepSeek-V3.1-Terminus deepseek | 1,417.1 | 1,407.38 – 1,426.82 | 3,609 |
| 103 | Qwen3-Next-80B-A3B-Instruct alibaba | 1,417.01 | 1,412.28 – 1,421.75 | 22,753 |
| 108 | Gemini 2.5 Flash google | 1,416.91 | 1,414.51 – 1,419.31 | 125,457 |
| 101 | DeepSeek-V3.1 (Thinking) deepseek | 1,416.6 | 1,409.97 – 1,423.22 | 11,458 |
| 108 | GPT-5.2 (High) openai | 1,416.25 | 1,412.74 – 1,419.77 | 49,628 |
| 108 | Gemini 3.1 Flash-Lite Preview google | 1,415.79 | 1,412.18 – 1,419.4 | 64,196 |
| 103 | Qwen3-235B-A22B-Thinking (2507) alibaba | 1,415.29 | 1,408.75 – 1,421.82 | 8,822 |
| 108 | amazon-nova-experimental-chat (11-10) amazon | 1,414.98 | 1,410.77 – 1,419.19 | 26,026 |
| 111 | Kimi K2 Thinking Turbo moonshot | 1,414.36 | 1,411.29 – 1,417.43 | 63,310 |
| 108 | Inkling-Small thinky | 1,414.32 | 1,409.82 – 1,418.82 | 36,999 |
| 108 | Qwen3-Max (2025-09-23) alibaba | 1,412.97 | 1,406.52 – 1,419.42 | 9,026 |
| 118 | GPT-5.2 openai | 1,412.28 | 1,409.14 – 1,415.43 | 83,793 |
| 118 | GPT-5.4 mini (High) openai | 1,411.58 | 1,407.87 – 1,415.3 | 63,432 |
| 118 | Grok 4 (0709) xai | 1,411.44 | 1,407.52 – 1,415.37 | 39,678 |
| 120 | MiMo-V2-Flash (Non-Thinking) xiaomi | 1,410.93 | 1,407.5 – 1,414.37 | 48,060 |
| 124 | o3 (2025-04-16) openai | 1,409.84 | 1,406.23 – 1,413.45 | 58,901 |
| 124 | Qwen3.5-27B alibaba | 1,408.99 | 1,404.72 – 1,413.26 | 28,647 |
| 130 | Grok 4.1 Fast (Reasoning) xai | 1,407.93 | 1,404.74 – 1,411.11 | 57,500 |
| 118 | Grok 4 Fast (Non-Reasoning) xai | 1,406.76 | 1,399.01 – 1,414.52 | 6,336 |
| 131 | Gemini 2.5 Flash Preview (09-2025) google | 1,406.47 | 1,402.45 – 1,410.49 | 32,996 |
| 131 | GPT-5 (High) openai | 1,406.15 | 1,401.73 – 1,410.57 | 31,718 |
| 110 | Hunyuan Vision 1.5 Thinking tencent | 1,405.78 | 1,393.38 – 1,418.17 | 2,169 |
| 120 | NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4) nvidia | 1,404.97 | 1,395.62 – 1,414.32 | 4,178 |
| 137 | MiniMax-M2.7 minimax | 1,404.79 | 1,401.51 – 1,408.07 | 89,197 |
| 138 | GPT-5 Chat openai | 1,403.28 | 1,399.01 – 1,407.54 | 31,187 |
| 142 | Step-3.5-Flash stepfun | 1,402.75 | 1,399.24 – 1,406.26 | 60,305 |
| 137 | Hy3 preview tencent | 1,401.17 | 1,393.79 – 1,408.56 | 6,869 |
| 137 | Claude Haiku 5.5 (High) anthropic | 1,400.88 | 1,393.38 – 1,408.39 | 7,890 |
| 134 | Hunyuan T1 (20250711) tencent | 1,400.68 | 1,392.03 – 1,409.32 | 4,595 |
| 141 | Qwen3-VL-235B-A22B-Thinking alibaba | 1,400.49 | 1,393.67 – 1,407.31 | 7,862 |
| 145 | Grok 4 Fast (Reasoning) xai | 1,399.6 | 1,394.56 – 1,404.65 | 18,270 |
| 145 | Grok 4.7 (xHigh) xai | 1,398.1 | 1,392.36 – 1,403.85 | 16,442 |
| 145 | GPT-6 Sol (Max) openai | 1,397.4 | 1,391.54 – 1,403.27 | 15,807 |
| 148 | Qwen3.5-Flash alibaba | 1,397.09 | 1,393.45 – 1,400.74 | 61,776 |
| 148 | Grok 4.3 xai | 1,396.88 | 1,393.27 – 1,400.48 | 71,287 |
| 148 | Claude Haiku 4.5 (20251001) anthropic | 1,396.87 | 1,394.5 – 1,399.25 | 154,063 |
| 143 | amazon-nova-experimental-chat (26-01-10) amazon | 1,395.76 | 1,386.15 – 1,405.36 | 3,534 |
| 148 | MiMo-V2-Flash (Thinking) xiaomi | 1,394.56 | 1,388.44 – 1,400.68 | 11,135 |
| 151 | Qwen3.5-35B-A3B alibaba | 1,394.54 | 1,390.34 – 1,398.74 | 30,427 |
| 148 | amazon-nova-experimental-chat (10-20) amazon | 1,393.92 | 1,387.86 – 1,399.98 | 11,625 |
| 151 | Qwen3-235B-A22B (Non-Thinking) alibaba | 1,393.46 | 1,388.96 – 1,397.96 | 37,472 |
| 151 | MiniMax-M2.1 Preview minimax | 1,391.99 | 1,386.92 – 1,397.07 | 17,222 |
| 151 | Muse Glimmer meta | 1,389.33 | 1,379.67 – 1,398.98 | 3,884 |
| 157 | GPT-6 Luna (Max) openai | 1,389.15 | 1,384.9 – 1,393.41 | 86,478 |
| 160 | GPT-5.3 Chat openai | 1,388.98 | 1,384.78 – 1,393.18 | 34,316 |
| 156 | Solar Pro 4 upstage | 1,388.52 | 1,383.5 – 1,393.53 | 26,159 |
| 165 | Qwen3-30B-A3B-Instruct (2507) alibaba | 1,383.78 | 1,378.9 – 1,388.66 | 23,312 |
| 166 | GLM-4.5-Air zai | 1,383.69 | 1,379.46 – 1,387.92 | 30,652 |
| 168 | GPT-4.1 (2025-04-14) openai | 1,382.93 | 1,379.24 – 1,386.63 | 50,298 |
| 168 | Kimi K2 Preview (0905) moonshot | 1,379.88 | 1,373.39 – 1,386.37 | 11,592 |
| 172 | Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025) google | 1,379.29 | 1,375.9 – 1,382.69 | 47,418 |
| 171 | NVIDIA-Nemotron-3-Super-120B-A12B nvidia | 1,377.38 | 1,370.32 – 1,384.43 | 7,870 |
| 171 | Hunyuan TurboS (20250416) tencent | 1,377.16 | 1,370.71 – 1,383.61 | 10,623 |
| 172 | Claude Opus 4 (Thinking 16K, 20250514) anthropic | 1,377.07 | 1,372.64 – 1,381.51 | 35,904 |
| 167 | GLM-4.6V zai | 1,376.48 | 1,365.34 – 1,387.62 | 2,833 |
| 176 | DeepSeek-V3 (0324) deepseek | 1,374.61 | 1,370.76 – 1,378.47 | 44,977 |
| 176 | GPT-5 mini (High) openai | 1,373.21 | 1,368.65 – 1,377.76 | 26,793 |
| 176 | DeepSeek-R1 deepseek | 1,372.65 | 1,367.81 – 1,377.5 | 18,524 |
| 177 | GPT-5.4 nano (High) openai | 1,371.98 | 1,368.23 – 1,375.74 | 62,314 |
| 177 | Kimi K2 Preview (0711) moonshot | 1,370.74 | 1,365.87 – 1,375.61 | 27,139 |
| 177 | Mistral Medium 3 (2505) mistral | 1,370.11 | 1,365.42 – 1,374.79 | 32,777 |
| 177 | Grok 3 Mini (High) xai | 1,369.5 | 1,364.06 – 1,374.94 | 15,595 |
| 177 | Gemini 2.5 Flash-Lite Preview (Thinking, 06-17) google | 1,369.21 | 1,364.72 – 1,373.69 | 32,381 |
| 177 | Qwen3-Next-80B-A3B-Thinking alibaba | 1,368.06 | 1,362.22 – 1,373.91 | 13,476 |
| 180 | Qwen2.5-Max alibaba | 1,366.64 | 1,362.55 – 1,370.73 | 32,487 |
| 179 | Qwen3-235B-A22B alibaba | 1,366.23 | 1,361.53 – 1,370.93 | 25,950 |
| 182 | Claude Opus 4 (20250514) anthropic | 1,365.96 | 1,361.63 – 1,370.29 | 43,037 |
| 182 | o1 (2024-12-17) openai | 1,365.79 | 1,361.32 – 1,370.27 | 27,807 |
| 182 | gpt-oss-120b openai | 1,365.46 | 1,361.11 – 1,369.8 | 30,200 |
| 182 | Grok 3 Mini Beta xai | 1,364.24 | 1,359.14 – 1,369.34 | 20,930 |
| 177 | amazon-nova-experimental-chat (10-09) amazon | 1,363.91 | 1,353.04 – 1,374.77 | 2,781 |
| 184 | Amazon Nova 2 Lite amazon | 1,361.93 | 1,355.93 – 1,367.94 | 12,415 |
| 179 | Granite 4.2 30B ibm | 1,361.42 | 1,350.97 – 1,371.87 | 3,389 |
| 183 | Ling-flash-2.0 ant-group | 1,361.11 | 1,353.9 – 1,368.32 | 6,952 |
| 190 | MiniMax-M2.5 minimax | 1,359.12 | 1,355.25 – 1,362.99 | 42,783 |
| 194 | Gemma 3 27B IT google | 1,357.72 | 1,354.06 – 1,361.37 | 46,670 |
| 193 | Qwen3-Coder-480B-A35B-Instruct alibaba | 1,356.59 | 1,351.6 – 1,361.58 | 25,190 |
| 190 | INTELLECT-3 Organization not supplied | 1,355.57 | 1,347.38 – 1,363.76 | 5,435 |
| 188 | Mercury 2 inception-ai | 1,354.79 | 1,344.42 – 1,365.16 | 3,191 |
| 197 | Gemini 2.0 Flash (001) google | 1,354.04 | 1,350.3 – 1,357.79 | 43,443 |
| 197 | o4-mini (2025-04-16) openai | 1,353.23 | 1,349.28 – 1,357.19 | 44,843 |
| 197 | o1-preview openai | 1,352.75 | 1,347.72 – 1,357.78 | 31,122 |
| 198 | Claude Sonnet 4 (Thinking 32K, 20250514) anthropic | 1,350.94 | 1,346.44 – 1,355.44 | 34,128 |
| 197 | GLM-4.7-Flash zai | 1,350.76 | 1,345.08 – 1,356.43 | 12,008 |
| 197 | Step-3 stepfun | 1,350.36 | 1,342.92 – 1,357.8 | 6,291 |
| 201 | NVIDIA-Nemotron-3-Nano-30B-A3B (BF16) nvidia | 1,347.84 | 1,342.45 – 1,353.23 | 15,761 |
| 208 | MiniMax-M1 minimax | 1,342.63 | 1,338.36 – 1,346.9 | 34,293 |
| 210 | GPT-4.1 mini (2025-04-14) openai | 1,340.49 | 1,336.18 – 1,344.79 | 38,696 |
| 210 | Trinity Large Thinking Organization not supplied | 1,340.28 | 1,335.65 – 1,344.92 | 30,290 |
| 206 | MiniMax-M2 minimax | 1,340.09 | 1,332.41 – 1,347.78 | 6,850 |
| 205 | Qwen3-32B alibaba | 1,340.06 | 1,330.76 – 1,349.37 | 3,926 |
| 211 | Claude Sonnet 4 (20250514) anthropic | 1,339.35 | 1,334.93 – 1,343.78 | 39,168 |
| 212 | Trinity Large Preview Organization not supplied | 1,338.61 | 1,334.37 – 1,342.85 | 31,233 |
| 206 | Llama 3.3 Nemotron Super 49B v1.5 nvidia | 1,338.12 | 1,328.14 – 1,348.1 | 3,327 |
| 211 | Mistral Small 3.2 (2506) mistral | 1,338.05 | 1,332.86 – 1,343.24 | 17,462 |
| 213 | o3-mini (High) openai | 1,336.55 | 1,331.31 – 1,341.8 | 18,589 |
| 212 | Step-1o Turbo (202506) stepfun | 1,335.62 | 1,328.77 – 1,342.48 | 8,906 |
| 211 | Gemma 3 12B IT google | 1,334.19 | 1,324.82 – 1,343.57 | 3,829 |
| 213 | Ring-flash-2.0 ant-group | 1,333.68 | 1,326.47 – 1,340.89 | 6,987 |
| 213 | GLM-4.5V zai | 1,332.63 | 1,324.21 – 1,341.06 | 4,817 |
| 214 | DeepSeek-V3 deepseek | 1,332.47 | 1,327.74 – 1,337.2 | 21,770 |
| 218 | Command A (03-2025) cohere | 1,330.9 | 1,327.45 – 1,334.35 | 55,763 |
| 215 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4) nvidia | 1,330.82 | 1,325.54 – 1,336.1 | 24,230 |
| 213 | GLM-4-Plus (0111) zai | 1,330.8 | 1,322.42 – 1,339.19 | 5,760 |
| 218 | Gemini 2.0 Flash-Lite Preview (02-05) google | 1,329.55 | 1,325.25 – 1,333.84 | 24,955 |
| 218 | QwQ-32B alibaba | 1,329.04 | 1,324.61 – 1,333.48 | 25,177 |
| 217 | Qwen-Plus (0125) alibaba | 1,326.38 | 1,318.1 – 1,334.67 | 5,819 |
| 222 | Step-2 16K Exp (202412) stepfun | 1,320.88 | 1,312.34 – 1,329.42 | 4,833 |
| 226 | GPT-5 nano (High) openai | 1,319.89 | 1,313.05 – 1,326.74 | 8,134 |
| 220 | Hunyuan TurboS (20250226) tencent | 1,319.71 | 1,308.01 – 1,331.41 | 2,220 |
| 221 | Llama 3.1 Nemotron Ultra 253B v1 nvidia | 1,319.52 | 1,308 – 1,331.03 | 2,549 |
| 232 | o3-mini openai | 1,319.41 | 1,315.86 – 1,322.96 | 56,735 |
| 232 | Gemini 1.5 Pro (002) google | 1,319.11 | 1,315.73 – 1,322.49 | 55,606 |
| 222 | Granite 4.2 8B ibm | 1,319.01 | 1,307.93 – 1,330.09 | 3,251 |
| 233 | o1-mini openai | 1,317.05 | 1,313.42 – 1,320.69 | 51,981 |
| 233 | Qwen3-30B-A3B alibaba | 1,316.96 | 1,312.24 – 1,321.67 | 26,156 |
| 233 | Claude 3.7 Sonnet (Thinking 32K, 20250219) anthropic | 1,314.27 | 1,310.02 – 1,318.51 | 38,156 |
| 232 | Hunyuan Turbo (0110) tencent | 1,311.4 | 1,299.97 – 1,322.83 | 2,290 |
| 234 | Olmo 3.1 32B Instruct allenai | 1,311.24 | 1,305.15 – 1,317.33 | 11,805 |
| 233 | Llama 3.3 Nemotron Super 49B v1 nvidia | 1,308.36 | 1,296.31 – 1,320.4 | 2,218 |
| 240 | Gemma 3n E4B IT google | 1,305.59 | 1,300.43 – 1,310.75 | 22,136 |
| 241 | Grok 2 (2024-08-13) xai | 1,304.55 | 1,300.89 – 1,308.21 | 63,498 |
| 244 | Yi Lightning Organization not supplied | 1,301.51 | 1,296.61 – 1,306.41 | 27,332 |
| 245 | GPT-4o (2024-05-13) openai | 1,300.41 | 1,296.98 – 1,303.85 | 112,881 |
| 245 | Claude 3.7 Sonnet (20250219) anthropic | 1,299.34 | 1,295.36 – 1,303.33 | 42,573 |
| 244 | Olmo 3 32B Think allenai | 1,299.34 | 1,291.09 – 1,307.58 | 5,827 |
| 244 | Qwen2.5-Plus (1127) alibaba | 1,299.12 | 1,292.8 – 1,305.45 | 10,187 |
| 245 | Claude 3.5 Sonnet (20241022) anthropic | 1,297.84 | 1,294.65 – 1,301.03 | 87,771 |
| 245 | DeepSeek-V2.5 (1210) deepseek | 1,293.9 | 1,285.68 – 1,302.12 | 6,795 |
| 245 | Granite 4.2 3B ibm | 1,293.31 | 1,281.82 – 1,304.81 | 3,249 |
| 251 | Athene V2 Chat Organization not supplied | 1,291.44 | 1,286.9 – 1,295.98 | 24,739 |
| 247 | Gemma 3 4B IT google | 1,290.78 | 1,281.55 – 1,300 | 4,171 |
| 246 | Granite 4.1 8B ibm | 1,290.53 | 1,280.61 – 1,300.45 | 4,177 |
| 253 | GLM-4-Plus zai | 1,289.63 | 1,284.73 – 1,294.53 | 26,126 |
| 248 | Hunyuan Large (2025-02-10) tencent | 1,287.93 | 1,278.2 – 1,297.66 | 3,738 |
| 241 | Molmo 2 8B allenai | 1,287.43 | 1,266.68 – 1,308.18 | 822 |
| 253 | gpt-oss-20b openai | 1,287.31 | 1,280.92 – 1,293.7 | 10,416 |
| 254 | Llama 4 Maverick 17B 128E Instruct meta | 1,287.21 | 1,282.96 – 1,291.47 | 39,439 |
| 255 | Gemini 1.5 Flash (002) google | 1,286.63 | 1,282.43 – 1,290.83 | 34,902 |
| 255 | GPT-4o mini (2024-07-18) openai | 1,286.35 | 1,282.83 – 1,289.87 | 68,705 |
| 254 | GPT-4.1 nano (2025-04-14) openai | 1,284.77 | 1,277.13 – 1,292.41 | 6,103 |
| 255 | Llama 3.1 405B Instruct (BF16) meta | 1,283.66 | 1,279.97 – 1,287.36 | 41,375 |
| 255 | Llama 3.1 Nemotron 70B Instruct nvidia | 1,282.63 | 1,274.93 – 1,290.33 | 7,140 |
| 256 | GPT-4o (2024-08-06) openai | 1,282.52 | 1,278.33 – 1,286.71 | 45,499 |
| 251 | Mercury inception-ai | 1,281.99 | 1,268.31 – 1,295.68 | 1,966 |
| 255 | Qwen-Max (0919) alibaba | 1,281.86 | 1,276.19 – 1,287.53 | 16,478 |
| 257 | Llama 3.1 405B Instruct (FP8) meta | 1,281.78 | 1,278.21 – 1,285.35 | 59,656 |
| 258 | Claude 3.5 Sonnet (20240620) anthropic | 1,280.9 | 1,277.48 – 1,284.31 | 82,419 |
| 258 | Grok 2 mini (2024-08-13) xai | 1,280.67 | 1,276.97 – 1,284.37 | 52,567 |
| 258 | Llama 4 Scout 17B 16E Instruct meta | 1,279.14 | 1,274.43 – 1,283.85 | 29,823 |
| 258 | Gemini Advanced (0514) google | 1,278.53 | 1,273.44 – 1,283.63 | 50,148 |
| 263 | Mistral Small 3.1 24B Instruct (2503) mistral | 1,277.02 | 1,272.49 – 1,281.55 | 32,722 |
| 269 | Llama 3.3 70B Instruct meta | 1,274.23 | 1,270.75 – 1,277.72 | 54,493 |
| 258 | Hunyuan Standard (2025-02-10) tencent | 1,273.97 | 1,264.33 – 1,283.62 | 3,904 |
| 270 | Gemini 1.5 Pro (001) google | 1,273.47 | 1,269.5 – 1,277.44 | 79,138 |
| 273 | GPT-4 Turbo (2024-04-09) openai | 1,271.67 | 1,267.77 – 1,275.56 | 98,114 |
| 266 | Olmo 3.1 32B Think allenai | 1,271.38 | 1,264.14 – 1,278.63 | 8,299 |
| 273 | DeepSeek-V2.5 deepseek | 1,271.23 | 1,266.55 – 1,275.91 | 24,572 |
| 276 | Qwen2.5-72B-Instruct alibaba | 1,269 | 1,264.93 – 1,273.06 | 39,406 |
| 278 | Mistral Large 2 (2407) mistral | 1,266.12 | 1,262.22 – 1,270.03 | 45,459 |
| 278 | Mistral Large (2411) mistral | 1,265.29 | 1,260.85 – 1,269.73 | 28,073 |
| 277 | Athene 70B (0725) Organization not supplied | 1,265.12 | 1,259.48 – 1,270.75 | 19,621 |
| 281 | GPT-4 Turbo Preview (1106) openai | 1,263.41 | 1,259.55 – 1,267.28 | 100,105 |
| 277 | Hunyuan Large Vision tencent | 1,262.85 | 1,253.6 – 1,272.1 | 5,279 |
| 283 | GPT-4 Turbo Preview (0125) openai | 1,262.18 | 1,258.1 – 1,266.26 | 93,439 |
| 283 | Claude 3 Opus (20240229) anthropic | 1,261.98 | 1,258.94 – 1,265.02 | 194,909 |
| 284 | Llama 3.1 70B Instruct meta | 1,260.88 | 1,257.17 – 1,264.6 | 55,240 |
| 286 | Amazon Nova Pro 1.0 amazon | 1,258.68 | 1,254.13 – 1,263.23 | 24,745 |
| 283 | Llama 3.1 Tulu 3 70B allenai | 1,255.7 | 1,245.25 – 1,266.15 | 2,846 |
| 291 | Claude 3.5 Haiku (20241022) anthropic | 1,255.39 | 1,252.16 – 1,258.62 | 69,056 |
| 287 | Magistral Medium (2506) mistral | 1,254.83 | 1,248.39 – 1,261.27 | 11,513 |
| 293 | Reka Core (20240904) Organization not supplied | 1,248.36 | 1,241.25 – 1,255.46 | 7,312 |
| 296 | Granite-4.0-H-Small ibm | 1,241.29 | 1,232.85 – 1,249.72 | 5,630 |
| 298 | Gemini 1.5 Flash (001) google | 1,239.28 | 1,234.81 – 1,243.74 | 62,833 |
| 298 | Jamba 1.5 Large Organization not supplied | 1,237 | 1,229.72 – 1,244.28 | 8,662 |
| 299 | Mistral Small 24B Instruct (2501) mistral | 1,233.54 | 1,227.66 – 1,239.41 | 14,681 |
| 300 | Gemma 2 27B IT google | 1,231.35 | 1,227.98 – 1,234.73 | 75,754 |
| 299 | Qwen2.5-Coder-32B-Instruct alibaba | 1,230.02 | 1,221.98 – 1,238.07 | 5,432 |
| 299 | Command R+ (08-2024) cohere | 1,228.87 | 1,222.33 – 1,235.42 | 9,866 |
| 300 | Amazon Nova Lite 1.0 amazon | 1,228.46 | 1,223.31 – 1,233.62 | 19,372 |
| 299 | Llama 3.1 Nemotron 51B Instruct nvidia | 1,227.97 | 1,218.04 – 1,237.9 | 3,749 |
| 300 | Gemma 2 9B IT SimPO Organization not supplied | 1,227.04 | 1,220.2 – 1,233.88 | 10,072 |
| 301 | GLM-4 (0520) zai | 1,225.89 | 1,218.96 – 1,232.81 | 9,788 |
| 301 | Gemini 1.5 Flash-8B (001) google | 1,225.83 | 1,221.55 – 1,230.11 | 35,558 |
| 301 | Nemotron-4 340B Instruct nvidia | 1,224.79 | 1,219.52 – 1,230.06 | 19,659 |
| 302 | Aya Expanse 32B cohere | 1,223.99 | 1,219.13 – 1,228.84 | 27,124 |
| 304 | Llama 3 70B Instruct meta | 1,220.77 | 1,217.19 – 1,224.35 | 156,876 |
| 307 | Claude 3 Sonnet (20240229) anthropic | 1,218.01 | 1,214.06 – 1,221.97 | 109,284 |
| 302 | OLMo 2 32B Instruct (0325) allenai | 1,217.91 | 1,207.14 – 1,228.69 | 3,334 |
| 304 | Reka Flash (20240904) Organization not supplied | 1,217.9 | 1,210.97 – 1,224.82 | 7,536 |
| 308 | Phi-4 microsoft | 1,216.66 | 1,212.08 – 1,221.24 | 24,126 |
| 315 | Amazon Nova Micro 1.0 amazon | 1,208.4 | 1,203.24 – 1,213.55 | 19,364 |
| 316 | Gemma 2 9B IT google | 1,207.37 | 1,203.57 – 1,211.17 | 54,611 |
| 317 | GPT-4 (0314) openai | 1,205.98 | 1,201.25 – 1,210.72 | 54,173 |
| 317 | Command R+ cohere | 1,203.81 | 1,199.52 – 1,208.09 | 77,554 |
| 317 | Qwen2-72B-Instruct alibaba | 1,203.25 | 1,198.35 – 1,208.15 | 37,325 |
| 315 | Hunyuan Standard 256K tencent | 1,201.91 | 1,190.35 – 1,213.46 | 2,728 |
| 322 | Claude 3 Haiku (20240307) anthropic | 1,194.66 | 1,190.92 – 1,198.39 | 117,701 |
| 318 | Llama 3.1 Tulu 3 8B allenai | 1,193.28 | 1,182.79 – 1,203.78 | 2,896 |
| 323 | DeepSeek-Coder-V2 deepseek | 1,191.17 | 1,184.83 – 1,197.5 | 15,147 |
| 321 | Ministral 8B (2410) mistral | 1,190.9 | 1,181.92 – 1,199.87 | 4,781 |
| 323 | Command R (08-2024) cohere | 1,187.34 | 1,180.82 – 1,193.85 | 10,140 |
| 323 | Jamba 1.5 Mini Organization not supplied | 1,186.65 | 1,179.49 – 1,193.81 | 8,858 |
| 324 | Llama 3.1 8B Instruct meta | 1,186.55 | 1,182.45 – 1,190.65 | 49,605 |
| 325 | GPT-4 (0613) openai | 1,185.98 | 1,181.95 – 1,190.01 | 88,723 |
| 323 | Aya Expanse 8B cohere | 1,185.09 | 1,178.17 – 1,192.01 | 9,818 |
| 330 | Mistral Large (2402) mistral | 1,176.45 | 1,171.77 – 1,181.14 | 62,436 |
| 331 | Qwen1.5-110B-Chat alibaba | 1,174.55 | 1,169.04 – 1,180.06 | 26,195 |
| 333 | Yi 1.5 34B Chat Organization not supplied | 1,172.93 | 1,167.94 – 1,177.93 | 24,146 |
| 333 | Reka Flash 21B (Online, 20240226) Organization not supplied | 1,170.41 | 1,163.1 – 1,177.71 | 15,450 |
| 334 | Qwen1.5-72B-Chat alibaba | 1,166.13 | 1,160.95 – 1,171.31 | 39,302 |
| 334 | Llama 3 8B Instruct meta | 1,165.58 | 1,161.86 – 1,169.29 | 104,642 |
| 334 | Mistral Medium mistral | 1,165.11 | 1,159.69 – 1,170.53 | 34,550 |
| 334 | Reka Flash 21B (20240226) Organization not supplied | 1,164.96 | 1,159.07 – 1,170.85 | 24,806 |
| 336 | Command R cohere | 1,163.11 | 1,158.38 – 1,167.84 | 54,036 |
| 336 | Mixtral 8x22B Instruct v0.1 mistral | 1,161.96 | 1,157.45 – 1,166.48 | 51,416 |
| 333 | QwQ-32B-Preview alibaba | 1,161.77 | 1,150.44 – 1,173.1 | 3,231 |
| 336 | InternLM2.5 20B Chat Organization not supplied | 1,158.42 | 1,151.37 – 1,165.47 | 9,901 |
| 339 | Gemma 2 2B IT google | 1,155.75 | 1,151.71 – 1,159.8 | 46,616 |
| 339 | Granite 3.1 8B Instruct ibm | 1,149.5 | 1,138.58 – 1,160.43 | 3,090 |
| 343 | Gemini Pro (Dev API) google | 1,148.82 | 1,141.63 – 1,156.02 | 18,354 |
| 343 | Zephyr ORPO 141B A35B v0.1 Organization not supplied | 1,143.67 | 1,132.95 – 1,154.38 | 4,652 |
| 346 | Phi-3 Medium 4K Instruct microsoft | 1,137.53 | 1,132.41 – 1,142.64 | 25,055 |
| 346 | Qwen1.5-32B-Chat alibaba | 1,137.18 | 1,131.11 – 1,143.25 | 21,741 |
| 347 | Starling LM 7B Beta Organization not supplied | 1,132.02 | 1,124.74 – 1,139.3 | 16,056 |
| 348 | Mixtral 8x7B Instruct v0.1 mistral | 1,131.53 | 1,127.31 – 1,135.76 | 73,503 |
| 346 | Gemini Pro google | 1,130.51 | 1,119.09 – 1,141.94 | 6,390 |
| 348 | Yi 34B Chat Organization not supplied | 1,128.45 | 1,121.68 – 1,135.21 | 15,483 |
| 348 | Qwen1.5-14B-Chat alibaba | 1,127.67 | 1,120.63 – 1,134.7 | 17,839 |
| 348 | Granite 3.1 2B Instruct ibm | 1,127.38 | 1,116.35 – 1,138.42 | 3,188 |
| 351 | GPT-3.5 Turbo (0125) openai | 1,124.9 | 1,120.23 – 1,129.56 | 66,207 |
| 351 | Tulu 2 DPO 70B Organization not supplied | 1,121.01 | 1,111.33 – 1,130.69 | 6,535 |
| 351 | WizardLM 70B microsoft | 1,119.5 | 1,110.17 – 1,128.82 | 8,214 |
| 352 | DBRX Instruct Preview Organization not supplied | 1,118.84 | 1,112.8 – 1,124.89 | 32,191 |
| 354 | Llama 2 70B Chat meta | 1,115.2 | 1,109.76 – 1,120.65 | 38,492 |
| 353 | Nous Hermes 2 Mixtral 8x7B DPO Organization not supplied | 1,112.01 | 1,100.24 – 1,123.79 | 3,777 |
| 358 | Phi-3 Small 8K Instruct microsoft | 1,109.8 | 1,103.96 – 1,115.64 | 17,766 |
| 357 | Llama 3.2 3B Instruct meta | 1,109.51 | 1,101.96 – 1,117.06 | 7,936 |
| 358 | Starling LM 7B Alpha Organization not supplied | 1,107.64 | 1,099.73 – 1,115.54 | 10,224 |
| 358 | OpenChat 3.5 (0106) Organization not supplied | 1,106.58 | 1,098.69 – 1,114.48 | 12,637 |
| 359 | Vicuna 33B Organization not supplied | 1,105.23 | 1,099.13 – 1,111.34 | 22,479 |
| 357 | DeepSeek LLM 67B Chat deepseek | 1,105 | 1,093.48 – 1,116.53 | 4,932 |
| 362 | Snowflake Arctic Instruct Organization not supplied | 1,100.95 | 1,095.07 – 1,106.83 | 32,832 |
| 360 | Llama 2 70B SteerLM Chat nvidia | 1,098.07 | 1,085.62 – 1,110.51 | 3,585 |
| 362 | OpenChat 3.5 Organization not supplied | 1,097.01 | 1,087.39 – 1,106.62 | 7,968 |
| 362 | Granite 3.0 8B Instruct ibm | 1,096.42 | 1,087.89 – 1,104.95 | 6,638 |
| 363 | GPT-3.5 Turbo (1106) openai | 1,094.1 | 1,085.38 – 1,102.81 | 16,619 |
| 365 | Gemma 1.1 7B IT google | 1,093.95 | 1,087.95 – 1,099.95 | 23,893 |
| 363 | OpenHermes 2.5 Mistral 7B Organization not supplied | 1,092.47 | 1,082.16 – 1,102.78 | 5,006 |
| 368 | Mistral 7B Instruct v0.2 mistral | 1,089.54 | 1,083 – 1,096.08 | 19,402 |
| 370 | Llama 2 13B Chat meta | 1,084.43 | 1,077.78 – 1,091.08 | 19,174 |
| 370 | Qwen1.5-7B-Chat alibaba | 1,083.43 | 1,073.74 – 1,093.12 | 4,737 |
| 368 | SOLAR 10.7B Instruct v1.0 upstage | 1,083.06 | 1,070.02 – 1,096.1 | 4,155 |
| 368 | Dolphin 2.2.1 Mistral 7B Organization not supplied | 1,080.95 | 1,065.67 – 1,096.23 | 1,679 |
| 373 | Phi-3 Mini 4K Instruct (June 2024) microsoft | 1,079.93 | 1,073.59 – 1,086.27 | 12,297 |
| 370 | Granite 3.0 2B Instruct ibm | 1,079.82 | 1,071.62 – 1,088.03 | 6,837 |
| 373 | WizardLM 13B microsoft | 1,076.51 | 1,067.29 – 1,085.73 | 7,044 |
| 377 | Phi-3 Mini 4K Instruct microsoft | 1,073.28 | 1,066.99 – 1,079.58 | 20,118 |
| 377 | Zephyr 7B Beta Organization not supplied | 1,069.4 | 1,060.7 – 1,078.09 | 11,118 |
| 377 | MPT 30B Chat Organization not supplied | 1,068.58 | 1,056.49 – 1,080.68 | 2,572 |
| 378 | Code Llama 34B Instruct meta | 1,065.46 | 1,056.7 – 1,074.22 | 7,366 |
| 378 | Zephyr 7B Alpha Organization not supplied | 1,058.34 | 1,042.69 – 1,074 | 1,785 |
| 385 | Vicuna 13B Organization not supplied | 1,057.63 | 1,051.05 – 1,064.21 | 19,367 |
| 378 | Code Llama 70B Instruct meta | 1,057.22 | 1,039.24 – 1,075.19 | 1,143 |
| 385 | Gemma 7B IT google | 1,056.13 | 1,046.61 – 1,065.65 | 8,925 |
| 385 | Llama 3.2 1B Instruct meta | 1,054.61 | 1,046.91 – 1,062.31 | 8,045 |
| 381 | Falcon 180B Chat Organization not supplied | 1,054.33 | 1,037.33 – 1,071.32 | 1,295 |
| 386 | Llama 2 7B Chat meta | 1,053.37 | 1,046.41 – 1,060.33 | 14,148 |
| 385 | Guanaco 33B Organization not supplied | 1,053.35 | 1,041.36 – 1,065.34 | 2,921 |
| 385 | Qwen-14B-Chat alibaba | 1,051 | 1,040.14 – 1,061.86 | 4,964 |
| 386 | Phi-3 Mini 128K Instruct microsoft | 1,050.36 | 1,043.15 – 1,057.58 | 20,685 |
| 388 | SmolLM2 1.7B Instruct Organization not supplied | 1,042 | 1,027.93 – 1,056.07 | 2,199 |
| 389 | StripedHyena Nous 7B Organization not supplied | 1,038.41 | 1,027.48 – 1,049.35 | 5,182 |
| 393 | OLMo 7B Instruct allenai | 1,031.78 | 1,020.76 – 1,042.81 | 6,328 |
| 396 | Vicuna 7B Organization not supplied | 1,030.92 | 1,021.85 – 1,039.99 | 6,923 |
| 398 | PaLM 2 google | 1,027.21 | 1,018.01 – 1,036.41 | 8,554 |
| 398 | Mistral 7B Instruct mistral | 1,023.48 | 1,014.32 – 1,032.64 | 8,977 |
| 398 | Gemma 1.1 2B IT google | 1,022.2 | 1,014.53 – 1,029.86 | 10,854 |
| 405 | Gemma 2B IT google | 1,002.12 | 990.65 – 1,013.59 | 4,780 |
| 405 | Qwen1.5-4B-Chat alibaba | 997.21 | 987.99 – 1,006.42 | 7,597 |
| 405 | Koala 13B Organization not supplied | 989.58 | 979.9 – 999.26 | 6,965 |
| 407 | ChatGLM3 6B Organization not supplied | 972.01 | 960.46 – 983.56 | 4,658 |
| 408 | GPT4All 13B Snoozy Organization not supplied | 956.15 | 941.16 – 971.15 | 1,743 |
| 408 | MPT 7B Chat Organization not supplied | 955.19 | 943.48 – 966.9 | 3,924 |
| 409 | RWKV-4 Raven 14B Organization not supplied | 948.36 | 937.13 – 959.59 | 4,845 |
| 409 | ChatGLM2 6B Organization not supplied | 938.6 | 925.17 – 952.03 | 2,658 |
| 409 | Alpaca 13B Organization not supplied | 932.78 | 921.53 – 944.03 | 5,745 |
| 412 | ChatGLM 6B Organization not supplied | 918.44 | 906.22 – 930.65 | 4,914 |
| 412 | OpenAssistant Pythia 12B Organization not supplied | 916.04 | 905.36 – 926.71 | 6,310 |
| 414 | FastChat-T5 3B Organization not supplied | 894.37 | 882.17 – 906.57 | 4,203 |
| 417 | StableLM Tuned Alpha 7B Organization not supplied | 866.55 | 854 – 879.09 | 3,287 |
| 417 | Dolly 2.0 12B Organization not supplied | 851.1 | 837.87 – 864.33 | 3,412 |
| 418 | LLaMA 13B meta | 833.48 | 817.95 – 849.02 | 2,391 |

## What this ranking can tell you

 - The population is the models in this source board, including variants and models without an available API price.
- Ranks use the published confidence bounds: one plus the number of models whose lower bound exceeds this model’s upper bound. Shared ranks are not proof of equal performance.

## Check the source

The original evidence is retained byte for byte. The downloadable board includes the source URLs, revision and SHA-256 hashes.

[Download this board and provenance →](/data/rankings/arena-text.json)

 Source files and licences - [metadata · a7a159f557a1](/data/rankings/evidence/a7a159f557a1e594a5d41218fe8d53c63c63daa39b655e51d6fc5b482a17d059.json) · [upstream source ↗](https://huggingface.co/api/datasets/lmarena-ai/leaderboard-dataset)
- [licence · 88a46d472f35](/data/rankings/evidence/88a46d472f35274fb6b7a852c3d16c8ee8007d51b37f290161537bec26895ee4.txt) · [upstream source ↗](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/raw/8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53/README.md)
- [rows · 2f2b2d089118](/data/rankings/evidence/2f2b2d0891188311d704e27a5b68c386bb085bdc7f38f2890e806aa67d5b0dbb.parquet) · [upstream source ↗](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53/text/latest-00000-of-00001.parquet)

[Explore other model types →](/rankings/)[Read the benchmark guide →](/benchmarks/)

## Continue your investigation

 - [Understand the measurements](/benchmarks/)
- [Compare task performance](/best/)
- [Compare embedding models](/embeddings/)
- [Inspect ranking rules](/methodology/)