421 models
| Rank | Model | Rating | Rating lower bound | Rating upper bound | Variance | Votes | Category | Source updated |
|---|---|---|---|---|---|---|---|---|
| #1 | Gemini 4 Carbon (High)google · Proprietary | 1,528.74 | 1,547.82 | 23.69 | 4,282 | overall | 2026-11-09 | |
| #2 | Gemini 4 Argon (High)google · Proprietary | 1,524.72 | 1,535.6 | 7.7 | 19,787 | overall | 2026-11-09 | |
| #3 | Claude Opus 5.5 (High)anthropic · Proprietary | 1,506.96 | 1,519.04 | 9.5 | 15,249 | overall | 2026-11-09 | |
| #4 | Claude Fable 5.1 (Max)anthropic · Proprietary | 1,506.84 | 1,517.92 | 7.98 | 20,087 | overall | 2026-11-09 | |
| #5 | Claude Opus 5 (Max)anthropic · Proprietary | 1,501.63 | 1,511.01 | 5.73 | 35,710 | overall | 2026-11-09 | |
| #6 | Muse Wonder (Max)meta · Proprietary | 1,496.72 | 1,509.38 | 10.43 | 12,032 | overall | 2026-11-09 | |
| #7 | Claude Opus 5 (High)anthropic · Proprietary | 1,498.65 | 1,505.87 | 3.39 | 73,697 | overall | 2026-11-09 | |
| #8 | Claude Opus 4.6 (High)anthropic · Proprietary | 1,498.42 | 1,504.9 | 2.73 | 84,424 | overall | 2026-11-09 | |
| #9 | Gemini 3.8 Flash (High)google · Proprietary | 1,496.18 | 1,504.64 | 4.66 | 61,143 | overall | 2026-11-09 | |
| #10 | Claude Opus 4.6anthropic · Proprietary | 1,493.58 | 1,499.91 | 2.61 | 89,228 | overall | 2026-11-09 | |
| #11 | MiMo-V2.6-Proxiaomi · MIT | 1,482.28 | 1,501.13 | 23.12 | 4,066 | overall | 2026-11-09 | |
| #12 | Claude Fable 5 (High)anthropic · Proprietary | 1,487.41 | 1,495.77 | 4.55 | 45,524 | overall | 2026-11-09 | |
| #13 | Muse Spark 1.3 (Max)meta · Proprietary | 1,486.42 | 1,496.52 | 6.65 | 26,111 | overall | 2026-11-09 | |
| #14 | Claude Opus 4.7 (High)anthropic · Proprietary | 1,485.96 | 1,493.46 | 3.67 | 64,308 | overall | 2026-11-09 | |
| #15 | Gemini 3.7 Flash (High)google · Proprietary | 1,484.14 | 1,493.49 | 5.69 | 33,300 | overall | 2026-11-09 | |
| #16 | Qwen3.8-Maxalibaba · Proprietary | 1,480.62 | 1,489.8 | 5.48 | 36,324 | overall | 2026-11-09 | |
| #17 | Muse Spark 1.2 (xHigh)meta · Proprietary | 1,478.14 | 1,489.86 | 8.95 | 15,004 | overall | 2026-11-09 | |
| #18 | Claude Opus 4.7anthropic · Proprietary | 1,479.44 | 1,486.96 | 3.69 | 65,369 | overall | 2026-11-09 | |
| #19 | Gemini 3.5 Flash (High)google · Proprietary | 1,479.05 | 1,486.83 | 3.94 | 47,642 | overall | 2026-11-09 | |
| #20 | Gemini 3.1 Pro Previewgoogle · Proprietary | 1,477.08 | 1,482.91 | 2.21 | 132,296 | overall | 2026-11-09 | |
| #21 | Gemini 3 Progoogle · Proprietary | 1,475.77 | 1,483.31 | 3.7 | 41,829 | overall | 2026-11-09 | |
| #22 | Gemini 3.6 Flash (High)google · Proprietary | 1,474.84 | 1,483.68 | 5.09 | 35,405 | overall | 2026-11-09 | |
| #23 | Muse Spark 1.1meta · Proprietary | 1,474.58 | 1,482.87 | 4.47 | 45,562 | overall | 2026-11-09 | |
| #24 | Gemini 3.5 Flash (Medium)google · Proprietary | 1,473.74 | 1,482.03 | 4.48 | 46,377 | overall | 2026-11-09 | |
| #25 | GLM-5.3 (Max)zai · MIT | 1,471.21 | 1,480.65 | 5.8 | 31,017 | overall | 2026-11-09 | |
| #26 | Qwen3.7-Max-Previewalibaba · Proprietary | 1,465.09 | 1,484.5 | 24.51 | 3,904 | overall | 2026-11-09 | |
| #27 | Kimi K3 (Max)moonshot · Kimi K3 license | 1,470.04 | 1,478.62 | 4.8 | 40,867 | overall | 2026-11-09 | |
| #28 | Muse Sparkmeta · Proprietary | 1,468.39 | 1,479.86 | 8.55 | 14,009 | overall | 2026-11-09 | |
| #29 | GPT-5.5 (High)openai · Proprietary | 1,467.48 | 1,474.89 | 3.57 | 68,359 | overall | 2026-11-09 | |
| #30 | Qwen3.5-Max-Previewalibaba · Proprietary | 1,466.08 | 1,475.81 | 6.17 | 22,419 | overall | 2026-11-09 | |
| #31 | GLM-5.3-Flashzai · MIT | 1,466.23 | 1,475.09 | 5.11 | 50,189 | overall | 2026-11-09 | |
| #32 | GLM-5.2 (Max)zai · MIT | 1,465.39 | 1,473.49 | 4.27 | 54,173 | overall | 2026-11-09 | |
| #33 | GPT-5.4 (High)openai · Proprietary | 1,465.36 | 1,472.86 | 3.66 | 64,103 | overall | 2026-11-09 | |
| #34 | Claude Sonnet 5.5 (xHigh)anthropic · Proprietary | 1,462.69 | 1,474.94 | 9.77 | 13,821 | overall | 2026-11-09 | |
| #35 | ERNIE 5.1baidu · Proprietary | 1,463.2 | 1,472.24 | 5.32 | 39,029 | overall | 2026-11-09 | |
| #36 | GPT-5.5openai · Proprietary | 1,462.45 | 1,469.79 | 3.51 | 69,937 | overall | 2026-11-09 | |
| #37 | Gemini 3 Flashgoogle · Proprietary | 1,461.52 | 1,470.17 | 4.87 | 31,133 | overall | 2026-11-09 | |
| #38 | MiMo-V2.5-Proxiaomi · MIT | 1,460.58 | 1,467.61 | 3.21 | 76,793 | overall | 2026-11-09 | |
| #39 | DeepSeek-V4.1-Flash-20260910 (Max)deepseek · MIT | 1,457.29 | 1,469.49 | 9.7 | 13,580 | overall | 2026-11-09 | |
| #40 | GLM-5.1zai · MIT | 1,459.19 | 1,466.22 | 3.21 | 67,074 | overall | 2026-11-09 | |
| #41 | Claude Opus 4.8 (High)anthropic · Proprietary | 1,457.52 | 1,465.29 | 3.94 | 63,128 | overall | 2026-11-09 | |
| #42 | Gemini 2.5 Progoogle · Proprietary | 1,455.44 | 1,460.32 | 1.55 | 124,789 | overall | 2026-11-09 | |
| #43 | Claude Sonnet 4.6anthropic · Proprietary | 1,454.27 | 1,461.28 | 3.2 | 70,017 | overall | 2026-11-09 | |
| #44 | Kimi K3.1 Pro (Max)moonshot · Kimi K3.1 Pro License | 1,446.67 | 1,467.95 | 29.49 | 3,443 | overall | 2026-11-09 | |
| #45 | GPT-5.6 Sol (xHigh)openai · Proprietary | 1,452.88 | 1,461.36 | 4.69 | 43,994 | overall | 2026-11-09 | |
| #46 | Kimi K2.6moonshot · Modified MIT | 1,450.94 | 1,459.77 | 5.08 | 39,573 | overall | 2026-11-09 | |
| #47 | Qwen3.7-Plusalibaba · Proprietary | 1,449.89 | 1,458.57 | 4.9 | 41,318 | overall | 2026-11-09 | |
| #48 | Claude Opus 4.8anthropic · Proprietary | 1,449.88 | 1,457.6 | 3.88 | 64,170 | overall | 2026-11-09 | |
| #49 | GPT-5.4openai · Proprietary | 1,448.81 | 1,456.14 | 3.5 | 67,105 | overall | 2026-11-09 | |
| #50 | DeepSeek-V4-Prodeepseek · MIT | 1,447.56 | 1,455.34 | 3.95 | 56,906 | overall | 2026-11-09 | |
| #51 | Grok 4.20 Beta (Reasoning, 0309)xai · Proprietary | 1,447.61 | 1,454.94 | 3.5 | 65,713 | overall | 2026-11-09 | |
| #52 | Claude Opus 4.5 (20251101)anthropic · Proprietary | 1,447.89 | 1,454.12 | 2.53 | 72,313 | overall | 2026-11-09 | |
| #53 | Grok 4.20 Multi-Agent Beta (0309)xai · Proprietary | 1,447.31 | 1,454.69 | 3.54 | 64,252 | overall | 2026-11-09 | |
| #54 | MiMo-V2.6-Flashxiaomi · MIT | 1,445.11 | 1,455.53 | 7.07 | 22,354 | overall | 2026-11-09 | |
| #55 | GPT-5.6 Terra (xHigh)openai · Proprietary | 1,444.59 | 1,452.89 | 4.48 | 48,825 | overall | 2026-11-09 | |
| #56 | Dola Seed 2.0 Probytedance · Proprietary | 1,445.25 | 1,451.93 | 2.9 | 78,230 | overall | 2026-11-09 | |
| #57 | amazon-nova-experimental-chat (26-02-10)amazon · Proprietary | 1,438.94 | 1,458.19 | 24.12 | 3,510 | overall | 2026-11-09 | |
| #58 | Claude Opus 4.5 (High, 32K, 20251101)anthropic · Proprietary | 1,444.46 | 1,452.13 | 3.83 | 37,253 | overall | 2026-11-09 | |
| #59 | Grok 4.5xai · Proprietary | 1,443.69 | 1,452.41 | 4.95 | 39,155 | overall | 2026-11-09 | |
| #60 | Qwen3.6-Max-Previewalibaba · Proprietary | 1,438.02 | 1,454.4 | 17.46 | 5,386 | overall | 2026-11-09 | |
| #61 | GLM-5zai · MIT | 1,441.9 | 1,450.35 | 4.65 | 29,020 | overall | 2026-11-09 | |
| #62 | GPT-6.1 Sol (Max)openai · Proprietary | 1,439.64 | 1,452.24 | 10.34 | 12,952 | overall | 2026-11-09 | |
| #63 | NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)nvidia · OpenMDW-1.1 | 1,438.31 | 1,452.08 | 12.33 | 11,399 | overall | 2026-11-09 | |
| #64 | DeepSeek-V4-Pro Preview (High)deepseek · MIT | 1,441.06 | 1,448.99 | 4.09 | 54,233 | overall | 2026-11-09 | |
| #65 | DeepSeek-V4-Pro (High, 20260813)deepseek · MIT | 1,438.33 | 1,451.57 | 11.42 | 9,584 | overall | 2026-11-09 | |
| #66 | Kimi K2.5 (Thinking)moonshot · Modified MIT | 1,441.42 | 1,447.95 | 2.77 | 73,872 | overall | 2026-11-09 | |
| #67 | Grok 4.20 Beta 1xai · Proprietary | 1,440 | 1,449.09 | 5.38 | 27,690 | overall | 2026-11-09 | |
| #68 | ERNIE 5.0 (0110)baidu · Proprietary | 1,440.37 | 1,448.1 | 3.89 | 36,175 | overall | 2026-11-09 | |
| #69 | Inklingthinky · Apache 2.0 | 1,439.48 | 1,447.61 | 4.3 | 50,137 | overall | 2026-11-09 | |
| #70 | Step 5 Previewstepfun · Proprietary | 1,436.87 | 1,449.35 | 10.14 | 12,362 | overall | 2026-11-09 | |
| #71 | ERNIE-5.0-Preview (1203)baidu · Proprietary | 1,436.14 | 1,449.11 | 10.94 | 9,740 | overall | 2026-11-09 | |
| #72 | GPT-5.1 (High)openai · Proprietary | 1,438.92 | 1,446.28 | 3.53 | 41,405 | overall | 2026-11-09 | |
| #73 | Gemma 4 31Bgoogle · Apache 2.0 | 1,435.13 | 1,449.94 | 14.27 | 6,130 | overall | 2026-11-09 | |
| #74 | Gemini 3 Flash (Minimal)google · Proprietary | 1,439.42 | 1,445.46 | 2.37 | 90,109 | overall | 2026-11-09 | |
| #75 | Claude Sonnet 5 (High)anthropic · Proprietary | 1,437.86 | 1,445.93 | 4.24 | 53,013 | overall | 2026-11-09 | |
| #76 | GLM-4.6zai · MIT | 1,436.36 | 1,444.14 | 3.94 | 35,652 | overall | 2026-11-09 | |
| #77 | GPT-6 Astra (Max)openai · Proprietary | 1,434.33 | 1,445.46 | 8.07 | 18,315 | overall | 2026-11-09 | |
| #78 | Qwen3-Max-Previewalibaba · Proprietary | 1,434.57 | 1,443.6 | 5.3 | 27,301 | overall | 2026-11-09 | |
| #79 | Hy3tencent · Apache 2.0 | 1,433.3 | 1,444.63 | 8.36 | 15,068 | overall | 2026-11-09 | |
| #80 | Claude Sonnet 4.5 (20250929)anthropic · Proprietary | 1,435.74 | 1,441.45 | 2.12 | 82,119 | overall | 2026-11-09 | |
| #81 | GPT-5.2 Chat (20260210)openai · Proprietary | 1,434.53 | 1,442.55 | 4.18 | 35,708 | overall | 2026-11-09 | |
| #82 | GLM-5V-Turbozai · Proprietary | 1,431.42 | 1,444.31 | 10.81 | 10,291 | overall | 2026-11-09 | |
| #83 | Qwen3.5-397B-A17Balibaba · Apache 2.0 | 1,434.54 | 1,440.61 | 2.39 | 97,678 | overall | 2026-11-09 | |
| #84 | Grok 4.1 (Thinking)xai · Proprietary | 1,433.5 | 1,439.8 | 2.58 | 66,074 | overall | 2026-11-09 | |
| #85 | MiMo-V2-Proxiaomi · Proprietary | 1,431.92 | 1,441.23 | 5.65 | 25,245 | overall | 2026-11-09 | |
| #86 | Qwen3.6-Plusalibaba · Proprietary | 1,432.09 | 1,440.33 | 4.42 | 47,601 | overall | 2026-11-09 | |
| #87 | Grok 4.1xai · Proprietary | 1,433.06 | 1,439.33 | 2.56 | 68,194 | overall | 2026-11-09 | |
| #88 | Qwen3.8-27Balibaba · Apache 2.0 | 1,431.49 | 1,440.72 | 5.54 | 32,659 | overall | 2026-11-09 | |
| #89 | GLM-4.7zai · MIT | 1,429.4 | 1,441.47 | 9.48 | 12,167 | overall | 2026-11-09 | |
| #90 | Gemini 3.5 Flash-Litegoogle · Proprietary | 1,430.05 | 1,439.04 | 5.27 | 35,114 | overall | 2026-11-09 | |
| #91 | Claude Sonnet 4.5 (High, 32K, 20250929)anthropic · Proprietary | 1,431.74 | 1,437.27 | 1.99 | 83,387 | overall | 2026-11-09 | |
| #92 | Gemma 4 26B A4Bgoogle · Apache 2.0 | 1,426.62 | 1,441.49 | 14.38 | 6,075 | overall | 2026-11-09 | |
| #93 | DeepSeek-V4-Flashdeepseek · MIT | 1,428.04 | 1,436.1 | 4.23 | 51,368 | overall | 2026-11-09 | |
| #94 | GPT-5.6 Luna (xHigh)openai · Proprietary | 1,426.71 | 1,435.31 | 4.82 | 40,641 | overall | 2026-11-09 | |
| #95 | GLM-4.5zai · MIT | 1,425.29 | 1,435.09 | 6.25 | 23,759 | overall | 2026-11-09 | |
| #96 | Grok 4.6 (High)xai · Proprietary | 1,425.23 | 1,434.54 | 5.65 | 34,616 | overall | 2026-11-09 | |
| #97 | ERNIE-5.0-Preview (1022)baidu · Proprietary | 1,421.01 | 1,438.53 | 19.98 | 4,737 | overall | 2026-11-09 | |
| #98 | Mistral Large 3mistral · Apache 2.0 | 1,425.83 | 1,431.41 | 2.03 | 88,641 | overall | 2026-11-09 | |
| #99 | ChatGPT-4o Latest (20250326)openai · Proprietary | 1,425.69 | 1,431.28 | 2.03 | 81,663 | overall | 2026-11-09 | |
| #100 | MiniMax-M3minimax · MiniMax Community License | 1,424.57 | 1,431.88 | 3.48 | 72,963 | overall | 2026-11-09 | |
| #101 | DeepSeek-R1 (0528)deepseek · MIT | 1,422.04 | 1,433.36 | 8.33 | 18,153 | overall | 2026-11-09 | |
| #102 | MiMo-V2.5xiaomi · MIT | 1,423.41 | 1,431.87 | 4.66 | 46,820 | overall | 2026-11-09 | |
| #103 | LongCat-Flash-Chat Exp (2602)meituan · Proprietary | 1,421.83 | 1,430.82 | 5.25 | 29,050 | overall | 2026-11-09 | |
| #104 | Grok 3 Preview (02-24)xai · Proprietary | 1,421.28 | 1,429.9 | 4.84 | 32,487 | overall | 2026-11-09 | |
| #105 | DeepSeek-V3.2-Exp (Thinking)deepseek · MIT | 1,418.52 | 1,431.64 | 11.21 | 8,966 | overall | 2026-11-09 | |
| #106 | Beam 1.0 501B A23Breflection · Apache 2.0 | 1,415.09 | 1,434.29 | 24 | 4,006 | overall | 2026-11-09 | |
| #107 | DeepSeek-V4-Flash Preview (High)deepseek · MIT | 1,420.44 | 1,428.64 | 4.37 | 51,195 | overall | 2026-11-09 | |
| #108 | Mistral Medium 3.1 (2508)mistral · Proprietary | 1,421.97 | 1,427.11 | 1.72 | 94,801 | overall | 2026-11-09 | |
| #109 | DeepSeek-V3.2deepseek · MIT | 1,421.06 | 1,428 | 3.14 | 47,790 | overall | 2026-11-09 | |
| #110 | MiMo-V2-Omnixiaomi · Proprietary | 1,417.09 | 1,428.2 | 8.03 | 20,411 | overall | 2026-11-09 | |
| #111 | LongCat-Flash-Chatmeituan · MIT | 1,416.06 | 1,428.86 | 10.66 | 11,131 | overall | 2026-11-09 | |
| #112 | DeepSeek-V3.2-Expdeepseek · MIT | 1,416.06 | 1,428.75 | 10.48 | 11,955 | overall | 2026-11-09 | |
| #113 | GPT-5.1openai · Proprietary | 1,418.75 | 1,425.87 | 3.3 | 44,207 | overall | 2026-11-09 | |
| #114 | Mistral Medium 3.5mistral · Modified MIT | 1,414.57 | 1,427.37 | 10.66 | 11,656 | overall | 2026-11-09 | |
| #115 | Kimi K2.5 (Instant)moonshot · Modified MIT | 1,414.13 | 1,427.08 | 10.9 | 8,323 | overall | 2026-11-09 | |
| #116 | DeepSeek-V3.2 (Thinking)deepseek · MIT | 1,416.5 | 1,423.62 | 3.3 | 41,782 | overall | 2026-11-09 | |
| #117 | Qwen3-VL-235B-A22B-Instructalibaba · Apache 2.0 | 1,413.5 | 1,426.52 | 11.03 | 11,288 | overall | 2026-11-09 | |
| #118 | DeepSeek-V3.1deepseek · MIT | 1,413.84 | 1,425.94 | 9.53 | 14,586 | overall | 2026-11-09 | |
| #119 | GPT-5.5 Instantopenai · Proprietary | 1,414.43 | 1,424.31 | 6.35 | 26,865 | overall | 2026-11-09 | |
| #120 | amazon-nova-experimental-chat (12-10)amazon · Proprietary | 1,409.92 | 1,428.78 | 23.15 | 3,715 | overall | 2026-11-09 | |
| #121 | Claude Opus 4.1 (Thinking 16K, 20250805)anthropic · Proprietary | 1,415.8 | 1,422.72 | 3.12 | 49,374 | overall | 2026-11-09 | |
| #122 | DeepSeek-V3.1-Terminus (Thinking)deepseek · MIT | 1,409.09 | 1,429.32 | 26.65 | 3,361 | overall | 2026-11-09 | |
| #123 | Qwen3-235B-A22B-Instruct (2507)alibaba · Apache 2.0 | 1,416.63 | 1,421.71 | 1.68 | 97,642 | overall | 2026-11-09 | |
| #124 | Claude Opus 4.1 (20250805)anthropic · Proprietary | 1,415.65 | 1,421.61 | 2.31 | 76,931 | overall | 2026-11-09 | |
| #125 | GPT-4.5 Preview (2025-02-27)openai · Proprietary | 1,411.69 | 1,423.06 | 8.42 | 14,547 | overall | 2026-11-09 | |
| #126 | Qwen3.5-122B-A10Balibaba · Apache 2.0 | 1,413.07 | 1,421.62 | 4.75 | 29,496 | overall | 2026-11-09 | |
| #127 | Qwen3-Next-80B-A3B-Instructalibaba · Apache 2.0 | 1,412.51 | 1,421.99 | 5.85 | 22,692 | overall | 2026-11-09 | |
| #128 | DeepSeek-V3.1-Terminusdeepseek · MIT | 1,407.49 | 1,426.95 | 24.65 | 3,605 | overall | 2026-11-09 | |
| #129 | Gemini 2.5 Flashgoogle · Proprietary | 1,414.58 | 1,419.39 | 1.51 | 124,953 | overall | 2026-11-09 | |
| #130 | DeepSeek-V3.1 (Thinking)deepseek · MIT | 1,410.06 | 1,423.31 | 11.43 | 11,441 | overall | 2026-11-09 | |
| #131 | GPT-5.2 (High)openai · Proprietary | 1,412.81 | 1,419.85 | 3.23 | 49,309 | overall | 2026-11-09 | |
| #132 | Gemini 3.1 Flash-Lite Previewgoogle · Proprietary | 1,412.36 | 1,419.6 | 3.42 | 63,629 | overall | 2026-11-09 | |
| #133 | Qwen3-235B-A22B-Thinking (2507)alibaba · Apache 2.0 | 1,409.01 | 1,422.08 | 11.13 | 8,812 | overall | 2026-11-09 | |
| #134 | amazon-nova-experimental-chat (11-10)amazon · Proprietary | 1,410.43 | 1,418.87 | 4.63 | 25,873 | overall | 2026-11-09 | |
| #135 | Kimi K2 Thinking Turbomoonshot · Modified MIT | 1,411.43 | 1,417.57 | 2.46 | 62,955 | overall | 2026-11-09 | |
| #136 | Mistral Large 4mistral · Modified MIT | 1,405.41 | 1,423.11 | 20.39 | 5,742 | overall | 2026-11-09 | |
| #137 | Inkling-Smallthinky · Apache 2.0 | 1,409.48 | 1,418.51 | 5.31 | 37,665 | overall | 2026-11-09 | |
| #138 | Qwen3-Max (2025-09-23)alibaba · Proprietary | 1,406.33 | 1,419.24 | 10.86 | 9,004 | overall | 2026-11-09 | |
| #139 | GPT-5.2openai · Proprietary | 1,408.93 | 1,415.24 | 2.59 | 82,951 | overall | 2026-11-09 | |
| #140 | GPT-5.4 mini (High)openai · Proprietary | 1,408.11 | 1,415.56 | 3.61 | 62,795 | overall | 2026-11-09 | |
| #141 | Grok 4 (0709)xai · Proprietary | 1,407.52 | 1,415.38 | 4.02 | 39,584 | overall | 2026-11-09 | |
| #142 | MiMo-V2-Flash (Non-Thinking)xiaomi · MIT | 1,407.83 | 1,414.71 | 3.08 | 47,783 | overall | 2026-11-09 | |
| #143 | o3 (2025-04-16)openai · Proprietary | 1,406.14 | 1,413.36 | 3.4 | 58,811 | overall | 2026-11-09 | |
| #144 | Qwen3.5-27Balibaba · Apache 2.0 | 1,404.54 | 1,413.1 | 4.77 | 28,424 | overall | 2026-11-09 | |
| #145 | Grok 4.1 Fast (Reasoning)xai · Proprietary | 1,405 | 1,411.38 | 2.65 | 57,133 | overall | 2026-11-09 | |
| #146 | NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)nvidia · OpenMDW-1.1 | 1,398.15 | 1,417.23 | 23.68 | 4,061 | overall | 2026-11-09 | |
| #147 | Grok 4 Fast (Non-Reasoning)xai · Proprietary | 1,399.2 | 1,414.72 | 15.68 | 6,330 | overall | 2026-11-09 | |
| #148 | Gemini 2.5 Flash Preview (09-2025)google · Proprietary | 1,402.48 | 1,410.53 | 4.22 | 32,868 | overall | 2026-11-09 | |
| #149 | GPT-5 (High)openai · Proprietary | 1,401.93 | 1,410.79 | 5.1 | 31,638 | overall | 2026-11-09 | |
| #150 | Hunyuan Vision 1.5 Thinkingtencent · Proprietary | 1,393.65 | 1,418.51 | 40.21 | 2,159 | overall | 2026-11-09 | |
| #151 | MiniMax-M2.7minimax · Modified MIT | 1,401.43 | 1,408 | 2.81 | 89,504 | overall | 2026-11-09 | |
| #152 | GPT-5 Chatopenai · Proprietary | 1,399.21 | 1,407.75 | 4.74 | 31,115 | overall | 2026-11-09 | |
| #153 | Inkling 2 Smallthinky · Proprietary | 1,391.43 | 1,414.92 | 35.89 | 2,668 | overall | 2026-11-09 | |
| #154 | Step-3.5-Flashstepfun · Apache 2.0 | 1,399.14 | 1,406.18 | 3.22 | 59,777 | overall | 2026-11-09 | |
| #155 | Hy3 previewtencent · tencent-hunyuan-community | 1,393.89 | 1,408.71 | 14.29 | 6,815 | overall | 2026-11-09 | |
| #156 | Hunyuan T1 (20250711)tencent · Proprietary | 1,392.11 | 1,409.42 | 19.51 | 4,584 | overall | 2026-11-09 | |
| #157 | Qwen3-VL-235B-A22B-Thinkingalibaba · Apache 2.0 | 1,393.69 | 1,407.37 | 12.18 | 7,835 | overall | 2026-11-09 | |
| #158 | Grok 4 Fast (Reasoning)xai · Proprietary | 1,394.53 | 1,404.63 | 6.65 | 18,206 | overall | 2026-11-09 | |
| #159 | Claude Haiku 5.5 (High)anthropic · Proprietary | 1,392.43 | 1,404.96 | 10.21 | 13,239 | overall | 2026-11-09 | |
| #160 | Grok 4.7 (xHigh)xai · Proprietary | 1,393.13 | 1,403.8 | 7.41 | 21,586 | overall | 2026-11-09 | |
| #161 | Qwen3.5-Flashalibaba · Proprietary | 1,393.48 | 1,400.79 | 3.48 | 61,168 | overall | 2026-11-09 | |
| #162 | Grok 4.3xai · Proprietary | 1,393.36 | 1,400.61 | 3.42 | 70,242 | overall | 2026-11-09 | |
| #163 | GPT-6 Sol (Max)openai · Proprietary | 1,391.04 | 1,402.04 | 7.87 | 19,890 | overall | 2026-11-09 | |
| #164 | Claude Haiku 4.5 (20251001)anthropic · Proprietary | 1,394.14 | 1,398.89 | 1.47 | 154,057 | overall | 2026-11-09 | |
| #165 | amazon-nova-experimental-chat (26-01-10)amazon · Proprietary | 1,385.38 | 1,404.64 | 24.14 | 3,523 | overall | 2026-11-09 | |
| #166 | Qwen3.5-35B-A3Balibaba · Apache 2.0 | 1,390.53 | 1,398.95 | 4.62 | 30,206 | overall | 2026-11-09 | |
| #167 | MiMo-V2-Flash (Thinking)xiaomi · MIT | 1,388.59 | 1,400.85 | 9.79 | 11,061 | overall | 2026-11-09 | |
| #168 | amazon-nova-experimental-chat (10-20)amazon · Proprietary | 1,388.17 | 1,400.31 | 9.59 | 11,558 | overall | 2026-11-09 | |
| #169 | Qwen3-235B-A22B (Non-Thinking)alibaba · Apache 2.0 | 1,389.06 | 1,398.07 | 5.29 | 37,416 | overall | 2026-11-09 | |
| #170 | MiniMax-M2.1 Previewminimax · MIT | 1,386.97 | 1,397.14 | 6.73 | 17,122 | overall | 2026-11-09 | |
| #171 | GPT-5.3 Chatopenai · Proprietary | 1,384.75 | 1,393.17 | 4.62 | 34,076 | overall | 2026-11-09 | |
| #172 | Muse Glimmermeta · Apache-2.0 | 1,379.13 | 1,398.63 | 24.76 | 3,793 | overall | 2026-11-09 | |
| #173 | GPT-6 Luna (Max)openai · Proprietary | 1,384.31 | 1,392.45 | 4.32 | 107,021 | overall | 2026-11-09 | |
| #174 | Solar Pro 4upstage · Proprietary | 1,383.17 | 1,393.22 | 6.57 | 27,104 | overall | 2026-11-09 | |
| #175 | Qwen3-30B-A3B-Instruct (2507)alibaba · Apache 2.0 | 1,378.96 | 1,388.72 | 6.2 | 23,287 | overall | 2026-11-09 | |
| #176 | GLM-4.5-Airzai · MIT | 1,379.44 | 1,387.9 | 4.66 | 30,591 | overall | 2026-11-09 | |
| #177 | GPT-4.1 (2025-04-14)openai · Proprietary | 1,379.21 | 1,386.6 | 3.56 | 50,235 | overall | 2026-11-09 | |
| #178 | Kimi K2 Preview (0905)moonshot · Modified MIT | 1,373.33 | 1,386.33 | 10.99 | 11,578 | overall | 2026-11-09 | |
| #179 | Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)google · Proprietary | 1,375.96 | 1,382.76 | 3.01 | 47,219 | overall | 2026-11-09 | |
| #180 | NVIDIA-Nemotron-3-Super-120B-A12Bnvidia · NVIDIA Open Model | 1,370.34 | 1,384.47 | 12.99 | 7,844 | overall | 2026-11-09 | |
| #181 | Hunyuan TurboS (20250416)tencent · Proprietary | 1,370.72 | 1,383.62 | 10.83 | 10,619 | overall | 2026-11-09 | |
| #182 | Claude Opus 4 (Thinking 16K, 20250514)anthropic · Proprietary | 1,372.71 | 1,381.59 | 5.13 | 35,852 | overall | 2026-11-09 | |
| #183 | GLM-4.6Vzai · MIT | 1,365.33 | 1,387.64 | 32.39 | 2,825 | overall | 2026-11-09 | |
| #184 | DeepSeek-V3 (0324)deepseek · MIT | 1,370.76 | 1,378.48 | 3.87 | 44,918 | overall | 2026-11-09 | |
| #185 | GPT-5 mini (High)openai · Proprietary | 1,368.8 | 1,377.93 | 5.42 | 26,718 | overall | 2026-11-09 | |
| #186 | DeepSeek-R1deepseek · MIT | 1,367.83 | 1,377.53 | 6.12 | 18,524 | overall | 2026-11-09 | |
| #187 | GPT-5.4 nano (High)openai · Proprietary | 1,368.01 | 1,375.55 | 3.7 | 61,636 | overall | 2026-11-09 | |
| #188 | Kimi K2 Preview (0711)moonshot · Modified MIT | 1,365.98 | 1,375.73 | 6.19 | 27,099 | overall | 2026-11-09 | |
| #189 | Mistral Medium 3 (2505)mistral · Proprietary | 1,365.46 | 1,374.84 | 5.72 | 32,751 | overall | 2026-11-09 | |
| #190 | Grok 3 Mini (High)xai · Proprietary | 1,364.08 | 1,374.97 | 7.71 | 15,574 | overall | 2026-11-09 | |
| #191 | Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)google · Proprietary | 1,364.88 | 1,373.86 | 5.25 | 32,330 | overall | 2026-11-09 | |
| #192 | Qwen3-Next-80B-A3B-Thinkingalibaba · Apache 2.0 | 1,362.48 | 1,374.17 | 8.9 | 13,450 | overall | 2026-11-09 | |
| #193 | Qwen2.5-Maxalibaba · Proprietary | 1,362.58 | 1,370.77 | 4.36 | 32,484 | overall | 2026-11-09 | |
| #194 | Qwen3-235B-A22Balibaba · Apache 2.0 | 1,361.54 | 1,370.95 | 5.76 | 25,927 | overall | 2026-11-09 | |
| #195 | Claude Opus 4 (20250514)anthropic · Proprietary | 1,361.7 | 1,370.38 | 4.9 | 42,967 | overall | 2026-11-09 | |
| #196 | o1 (2024-12-17)openai · Proprietary | 1,361.35 | 1,370.3 | 5.22 | 27,807 | overall | 2026-11-09 | |
| #197 | gpt-oss-120bopenai · Apache 2.0 | 1,361.11 | 1,369.82 | 4.94 | 30,133 | overall | 2026-11-09 | |
| #198 | Grok 3 Mini Betaxai · Proprietary | 1,359.16 | 1,369.37 | 6.78 | 20,910 | overall | 2026-11-09 | |
| #199 | amazon-nova-experimental-chat (10-09)amazon · Proprietary | 1,352.85 | 1,374.6 | 30.81 | 2,776 | overall | 2026-11-09 | |
| #200 | Amazon Nova 2 Liteamazon · Proprietary | 1,355.83 | 1,367.87 | 9.44 | 12,340 | overall | 2026-11-09 | |
| #201 | Granite 4.2 30Bibm · Apache 2.0 | 1,350.62 | 1,371.75 | 29.04 | 3,314 | overall | 2026-11-09 | |
| #202 | Ling-flash-2.0ant-group · MIT | 1,353.76 | 1,368.18 | 13.55 | 6,937 | overall | 2026-11-09 | |
| #203 | MiniMax-M2.5minimax · Modified MIT | 1,355.42 | 1,363.18 | 3.92 | 42,459 | overall | 2026-11-09 | |
| #204 | Gemma 3 27B ITgoogle · Gemma | 1,354.12 | 1,361.45 | 3.49 | 46,613 | overall | 2026-11-09 | |
| #205 | Qwen3-Coder-480B-A35B-Instructalibaba · Apache 2.0 | 1,351.58 | 1,361.58 | 6.5 | 25,155 | overall | 2026-11-09 | |
| #206 | INTELLECT-3MIT | 1,347.79 | 1,364.22 | 17.57 | 5,403 | overall | 2026-11-09 | |
| #207 | Mercury 2inception-ai · Proprietary | 1,344.38 | 1,365.22 | 28.27 | 3,158 | overall | 2026-11-09 | |
| #208 | Gemini 2.0 Flash (001)google · Proprietary | 1,350.36 | 1,357.87 | 3.66 | 43,428 | overall | 2026-11-09 | |
| #209 | o4-mini (2025-04-16)openai · Proprietary | 1,349.21 | 1,357.13 | 4.08 | 44,801 | overall | 2026-11-09 | |
| #210 | o1-previewopenai · Proprietary | 1,347.75 | 1,357.81 | 6.58 | 31,122 | overall | 2026-11-09 | |
| #211 | Claude Sonnet 4 (Thinking 32K, 20250514)anthropic · Proprietary | 1,346.33 | 1,355.33 | 5.28 | 34,078 | overall | 2026-11-09 | |
| #212 | GLM-4.7-Flashzai · MIT | 1,344.88 | 1,356.26 | 8.42 | 11,937 | overall | 2026-11-09 | |
| #213 | Step-3stepfun · Apache 2.0 | 1,342.64 | 1,357.53 | 14.44 | 6,279 | overall | 2026-11-09 | |
| #214 | NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)nvidia · NVIDIA Open Model | 1,342.69 | 1,353.49 | 7.59 | 15,663 | overall | 2026-11-09 | |
| #215 | MiniMax-M1minimax · Apache 2.0 | 1,338.31 | 1,346.86 | 4.76 | 34,242 | overall | 2026-11-09 | |
| #216 | GPT-4.1 mini (2025-04-14)openai · Proprietary | 1,336.22 | 1,344.84 | 4.83 | 38,657 | overall | 2026-11-09 | |
| #217 | MiniMax-M2minimax · Apache 2.0 | 1,332.58 | 1,347.96 | 15.4 | 6,832 | overall | 2026-11-09 | |
| #218 | Trinity Large ThinkingApache 2.0 | 1,335.54 | 1,344.84 | 5.62 | 30,045 | overall | 2026-11-09 | |
| #219 | Qwen3-32Balibaba · Apache 2.0 | 1,330.77 | 1,349.38 | 22.56 | 3,926 | overall | 2026-11-09 | |
| #220 | Claude Sonnet 4 (20250514)anthropic · Proprietary | 1,334.87 | 1,343.73 | 5.11 | 39,126 | overall | 2026-11-09 | |
| #221 | Trinity Large PreviewApache 2.0 | 1,334.65 | 1,343.14 | 4.69 | 31,031 | overall | 2026-11-09 | |
| #222 | Mistral Small 3.2 (2506)mistral · Apache 2.0 | 1,333.11 | 1,343.5 | 7.02 | 17,437 | overall | 2026-11-09 | |
| #223 | Llama 3.3 Nemotron Super 49B v1.5nvidia · Nvidia Open | 1,328.29 | 1,348.26 | 25.96 | 3,324 | overall | 2026-11-09 | |
| #224 | o3-mini (High)openai · Proprietary | 1,331.34 | 1,341.83 | 7.17 | 18,589 | overall | 2026-11-09 | |
| #225 | Step-1o Turbo (202506)stepfun · Proprietary | 1,328.74 | 1,342.46 | 12.24 | 8,900 | overall | 2026-11-09 | |
| #226 | Gemma 3 12B ITgoogle · Gemma | 1,324.84 | 1,343.58 | 22.87 | 3,829 | overall | 2026-11-09 | |
| #227 | Ring-flash-2.0ant-group · MIT | 1,326.46 | 1,340.9 | 13.57 | 6,970 | overall | 2026-11-09 | |
| #228 | GLM-4.5Vzai · MIT | 1,324.11 | 1,340.97 | 18.49 | 4,813 | overall | 2026-11-09 | |
| #229 | DeepSeek-V3deepseek · DeepSeek | 1,327.77 | 1,337.24 | 5.84 | 21,770 | overall | 2026-11-09 | |
| #230 | Command A (03-2025)cohere · CC-BY-NC-4.0 | 1,327.5 | 1,334.41 | 3.11 | 55,679 | overall | 2026-11-09 | |
| #231 | GLM-4-Plus (0111)zai · Proprietary | 1,322.45 | 1,339.22 | 18.31 | 5,760 | overall | 2026-11-09 | |
| #232 | Gemini 2.0 Flash-Lite Preview (02-05)google · Proprietary | 1,325.28 | 1,333.87 | 4.81 | 24,955 | overall | 2026-11-09 | |
| #233 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4)nvidia · OpenMDW-1.1 | 1,324.08 | 1,334.66 | 7.29 | 25,129 | overall | 2026-11-09 | |
| #234 | QwQ-32Balibaba · Apache 2.0 | 1,324.64 | 1,333.51 | 5.13 | 25,166 | overall | 2026-11-09 | |
| #235 | Qwen-Plus (0125)alibaba · Proprietary | 1,318.14 | 1,334.7 | 17.85 | 5,819 | overall | 2026-11-09 | |
| #236 | Step-2 16K Exp (202412)stepfun · Proprietary | 1,312.37 | 1,329.45 | 18.98 | 4,833 | overall | 2026-11-09 | |
| #237 | GPT-5 nano (High)openai · Proprietary | 1,313.14 | 1,326.85 | 12.22 | 8,126 | overall | 2026-11-09 | |
| #238 | Hunyuan TurboS (20250226)tencent · Proprietary | 1,308.05 | 1,331.45 | 35.62 | 2,220 | overall | 2026-11-09 | |
| #239 | Llama 3.1 Nemotron Ultra 253B v1nvidia · Nvidia Open Model | 1,308.01 | 1,331.04 | 34.52 | 2,549 | overall | 2026-11-09 | |
| #240 | o3-miniopenai · Proprietary | 1,315.96 | 1,323.07 | 3.29 | 56,692 | overall | 2026-11-09 | |
| #241 | Gemini 1.5 Pro (002)google · Proprietary | 1,315.76 | 1,322.52 | 2.97 | 55,606 | overall | 2026-11-09 | |
| #242 | Granite 4.2 8Bibm · Apache 2.0 | 1,307.64 | 1,330 | 32.54 | 3,196 | overall | 2026-11-09 | |
| #243 | o1-miniopenai · Proprietary | 1,313.45 | 1,320.72 | 3.44 | 51,981 | overall | 2026-11-09 | |
| #244 | Qwen3-30B-A3Balibaba · Apache 2.0 | 1,312.07 | 1,321.51 | 5.79 | 26,137 | overall | 2026-11-09 | |
| #245 | Claude 3.7 Sonnet (Thinking 32K, 20250219)anthropic · Proprietary | 1,310.11 | 1,318.6 | 4.69 | 38,126 | overall | 2026-11-09 | |
| #246 | Hunyuan Turbo (0110)tencent · Proprietary | 1,300.01 | 1,322.87 | 34 | 2,290 | overall | 2026-11-09 | |
| #247 | Olmo 3.1 32B Instructallenai · Apache 2.0 | 1,305.05 | 1,317.25 | 9.69 | 11,738 | overall | 2026-11-09 | |
| #248 | Llama 3.3 Nemotron Super 49B v1nvidia · Nvidia | 1,296.35 | 1,320.44 | 37.76 | 2,218 | overall | 2026-11-09 | |
| #249 | Gemma 3n E4B ITgoogle · Gemma | 1,300.4 | 1,310.73 | 6.94 | 22,106 | overall | 2026-11-09 | |
| #250 | Grok 2 (2024-08-13)xai · Proprietary | 1,300.92 | 1,308.24 | 3.49 | 63,498 | overall | 2026-11-09 | |
| #251 | Yi LightningProprietary | 1,296.64 | 1,306.44 | 6.24 | 27,332 | overall | 2026-11-09 | |
| #252 | GPT-4o (2024-05-13)openai · Proprietary | 1,297.01 | 1,303.88 | 3.07 | 112,881 | overall | 2026-11-09 | |
| #253 | Claude 3.7 Sonnet (20250219)anthropic · Proprietary | 1,295.26 | 1,303.24 | 4.14 | 42,553 | overall | 2026-11-09 | |
| #254 | Qwen2.5-Plus (1127)alibaba · Proprietary | 1,292.83 | 1,305.48 | 10.42 | 10,187 | overall | 2026-11-09 | |
| #255 | Olmo 3 32B Thinkallenai · Apache 2.0 | 1,290.83 | 1,307.36 | 17.8 | 5,794 | overall | 2026-11-09 | |
| #256 | Claude 3.5 Sonnet (20241022)anthropic · Proprietary | 1,294.67 | 1,301.06 | 2.65 | 87,743 | overall | 2026-11-09 | |
| #257 | DeepSeek-V2.5 (1210)deepseek · DeepSeek | 1,285.71 | 1,302.15 | 17.6 | 6,795 | overall | 2026-11-09 | |
| #258 | Granite 4.2 3Bibm · Apache 2.0 | 1,280.9 | 1,304.15 | 35.19 | 3,185 | overall | 2026-11-09 | |
| #259 | Athene V2 ChatNexusFlow | 1,286.93 | 1,296.01 | 5.37 | 24,739 | overall | 2026-11-09 | |
| #260 | Granite 4.1 8Bibm · Apache 2.0 | 1,280.92 | 1,300.82 | 25.78 | 4,138 | overall | 2026-11-09 | |
| #261 | Gemma 3 4B ITgoogle · Gemma | 1,281.57 | 1,300.02 | 22.16 | 4,171 | overall | 2026-11-09 | |
| #262 | GLM-4-Pluszai · Proprietary | 1,284.76 | 1,294.56 | 6.25 | 26,126 | overall | 2026-11-09 | |
| #263 | Hunyuan Large (2025-02-10)tencent · Proprietary | 1,278.24 | 1,297.69 | 24.64 | 3,738 | overall | 2026-11-09 | |
| #264 | gpt-oss-20bopenai · Apache 2.0 | 1,281.21 | 1,293.99 | 10.64 | 10,400 | overall | 2026-11-09 | |
| #265 | Llama 4 Maverick 17B 128E Instructmeta · Llama 4 | 1,283 | 1,291.52 | 4.72 | 39,397 | overall | 2026-11-09 | |
| #266 | Molmo 2 8Ballenai · Apache 2.0 | 1,265.94 | 1,307.52 | 112.49 | 820 | overall | 2026-11-09 | |
| #267 | Gemini 1.5 Flash (002)google · Proprietary | 1,282.46 | 1,290.86 | 4.6 | 34,902 | overall | 2026-11-09 | |
| #268 | GPT-4o mini (2024-07-18)openai · Proprietary | 1,282.86 | 1,289.91 | 3.23 | 68,705 | overall | 2026-11-09 | |
| #269 | GPT-4.1 nano (2025-04-14)openai · Proprietary | 1,277.15 | 1,292.43 | 15.2 | 6,103 | overall | 2026-11-09 | |
| #270 | Llama 3.1 405B Instruct (BF16)meta · Llama 3.1 Community | 1,280 | 1,287.39 | 3.56 | 41,375 | overall | 2026-11-09 | |
| #271 | Llama 3.1 Nemotron 70B Instructnvidia · Llama 3.1 | 1,274.96 | 1,290.37 | 15.45 | 7,140 | overall | 2026-11-09 | |
| #272 | GPT-4o (2024-08-06)openai · Proprietary | 1,278.36 | 1,286.74 | 4.57 | 45,499 | overall | 2026-11-09 | |
| #273 | Qwen-Max (0919)alibaba · Qwen | 1,276.22 | 1,287.56 | 8.37 | 16,478 | overall | 2026-11-09 | |
| #274 | Mercuryinception-ai · Proprietary | 1,268.12 | 1,295.51 | 48.83 | 1,963 | overall | 2026-11-09 | |
| #275 | Llama 3.1 405B Instruct (FP8)meta · Llama 3.1 Community | 1,278.24 | 1,285.38 | 3.32 | 59,656 | overall | 2026-11-09 | |
| #276 | Claude 3.5 Sonnet (20240620)anthropic · Proprietary | 1,277.51 | 1,284.35 | 3.04 | 82,419 | overall | 2026-11-09 | |
| #277 | Grok 2 mini (2024-08-13)xai · Proprietary | 1,277 | 1,284.4 | 3.57 | 52,567 | overall | 2026-11-09 | |
| #278 | Llama 4 Scout 17B 16E Instructmeta · Llama | 1,274.49 | 1,283.92 | 5.79 | 29,777 | overall | 2026-11-09 | |
| #279 | Gemini Advanced (0514)google · Proprietary | 1,273.47 | 1,283.66 | 6.75 | 50,148 | overall | 2026-11-09 | |
| #280 | Mistral Small 3.1 24B Instruct (2503)mistral · Apache 2.0 | 1,272.61 | 1,281.68 | 5.35 | 32,666 | overall | 2026-11-09 | |
| #281 | Llama 3.3 70B Instructmeta · Llama-3.3 | 1,270.76 | 1,277.73 | 3.16 | 54,482 | overall | 2026-11-09 | |
| #282 | Hunyuan Standard (2025-02-10)tencent · Proprietary | 1,264.37 | 1,283.65 | 24.19 | 3,904 | overall | 2026-11-09 | |
| #283 | Gemini 1.5 Pro (001)google · Proprietary | 1,269.54 | 1,277.47 | 4.09 | 79,138 | overall | 2026-11-09 | |
| #284 | GPT-4 Turbo (2024-04-09)openai · Proprietary | 1,267.8 | 1,275.59 | 3.95 | 98,114 | overall | 2026-11-09 | |
| #285 | DeepSeek-V2.5deepseek · DeepSeek | 1,266.58 | 1,275.94 | 5.7 | 24,572 | overall | 2026-11-09 | |
| #286 | Olmo 3.1 32B Thinkallenai · Apache 2.0 | 1,263.75 | 1,278.28 | 13.75 | 8,244 | overall | 2026-11-09 | |
| #287 | Qwen2.5-72B-Instructalibaba · Qwen | 1,264.96 | 1,273.09 | 4.3 | 39,406 | overall | 2026-11-09 | |
| #288 | Mistral Large 2 (2407)mistral · Mistral Research | 1,262.25 | 1,270.06 | 3.97 | 45,459 | overall | 2026-11-09 | |
| #289 | Mistral Large (2411)mistral · MRL | 1,260.88 | 1,269.76 | 5.13 | 28,073 | overall | 2026-11-09 | |
| #290 | Athene 70B (0725)CC-BY-NC-4.0 | 1,259.51 | 1,270.79 | 8.27 | 19,621 | overall | 2026-11-09 | |
| #291 | GPT-4 Turbo Preview (1106)openai · Proprietary | 1,259.59 | 1,267.31 | 3.88 | 100,105 | overall | 2026-11-09 | |
| #292 | Hunyuan Large Visiontencent · Proprietary | 1,253.81 | 1,272.32 | 22.3 | 5,273 | overall | 2026-11-09 | |
| #293 | GPT-4 Turbo Preview (0125)openai · Proprietary | 1,258.13 | 1,266.29 | 4.33 | 93,439 | overall | 2026-11-09 | |
| #294 | Claude 3 Opus (20240229)anthropic · Proprietary | 1,258.97 | 1,265.05 | 2.41 | 194,909 | overall | 2026-11-09 | |
| #295 | Llama 3.1 70B Instructmeta · Llama 3.1 Community | 1,257.2 | 1,264.63 | 3.59 | 55,240 | overall | 2026-11-09 | |
| #296 | Amazon Nova Pro 1.0amazon · Proprietary | 1,254.15 | 1,263.26 | 5.39 | 24,745 | overall | 2026-11-09 | |
| #297 | Llama 3.1 Tulu 3 70Ballenai · Llama 3.1 | 1,245.28 | 1,266.18 | 28.43 | 2,846 | overall | 2026-11-09 | |
| #298 | Claude 3.5 Haiku (20241022)anthropic · Proprietary | 1,252.16 | 1,258.62 | 2.72 | 69,014 | overall | 2026-11-09 | |
| #299 | Magistral Medium (2506)mistral · Proprietary | 1,248.32 | 1,261.21 | 10.81 | 11,496 | overall | 2026-11-09 | |
| #300 | Reka Core (20240904)Proprietary | 1,241.28 | 1,255.49 | 13.14 | 7,312 | overall | 2026-11-09 | |
| #301 | Granite-4.0-H-Smallibm · Apache 2.0 | 1,233.06 | 1,249.95 | 18.56 | 5,614 | overall | 2026-11-09 | |
| #302 | Gemini 1.5 Flash (001)google · Proprietary | 1,234.84 | 1,243.77 | 5.19 | 62,833 | overall | 2026-11-09 | |
| #303 | Jamba 1.5 LargeJamba Open | 1,229.75 | 1,244.31 | 13.8 | 8,662 | overall | 2026-11-09 | |
| #304 | Mistral Small 24B Instruct (2501)mistral · Apache 2.0 | 1,227.69 | 1,239.44 | 8.99 | 14,681 | overall | 2026-11-09 | |
| #305 | Gemma 2 27B ITgoogle · Gemma license | 1,228.01 | 1,234.76 | 2.96 | 75,754 | overall | 2026-11-09 | |
| #306 | Qwen2.5-Coder-32B-Instructalibaba · Apache 2.0 | 1,222.01 | 1,238.1 | 16.85 | 5,432 | overall | 2026-11-09 | |
| #307 | Command R+ (08-2024)cohere · CC-BY-NC-4.0 | 1,222.37 | 1,235.45 | 11.14 | 9,866 | overall | 2026-11-09 | |
| #308 | Amazon Nova Lite 1.0amazon · Proprietary | 1,223.34 | 1,233.65 | 6.92 | 19,372 | overall | 2026-11-09 | |
| #309 | Llama 3.1 Nemotron 51B Instructnvidia · Llama 3.1 | 1,218.07 | 1,237.93 | 25.67 | 3,749 | overall | 2026-11-09 | |
| #310 | Gemma 2 9B IT SimPOMIT | 1,220.23 | 1,233.91 | 12.18 | 10,072 | overall | 2026-11-09 | |
| #311 | GLM-4 (0520)zai · Proprietary | 1,219 | 1,232.84 | 12.46 | 9,788 | overall | 2026-11-09 | |
| #312 | Gemini 1.5 Flash-8B (001)google · Proprietary | 1,221.58 | 1,230.14 | 4.77 | 35,558 | overall | 2026-11-09 | |
| #313 | Nemotron-4 340B Instructnvidia · NVIDIA Open Model | 1,219.55 | 1,230.09 | 7.24 | 19,659 | overall | 2026-11-09 | |
| #314 | Aya Expanse 32Bcohere · CC-BY-NC-4.0 | 1,219.16 | 1,228.87 | 6.15 | 27,124 | overall | 2026-11-09 | |
| #315 | Llama 3 70B Instructmeta · Llama 3 Community | 1,217.23 | 1,224.38 | 3.33 | 156,876 | overall | 2026-11-09 | |
| #316 | Claude 3 Sonnet (20240229)anthropic · Proprietary | 1,214.09 | 1,222 | 4.07 | 109,284 | overall | 2026-11-09 | |
| #317 | OLMo 2 32B Instruct (0325)allenai · Apache-2.0 | 1,207.16 | 1,228.71 | 30.22 | 3,334 | overall | 2026-11-09 | |
| #318 | Reka Flash (20240904)Proprietary | 1,211 | 1,224.85 | 12.49 | 7,536 | overall | 2026-11-09 | |
| #319 | Phi-4microsoft · MIT | 1,212.11 | 1,221.28 | 5.47 | 24,126 | overall | 2026-11-09 | |
| #320 | Amazon Nova Micro 1.0amazon · Proprietary | 1,203.28 | 1,213.59 | 6.92 | 19,364 | overall | 2026-11-09 | |
| #321 | Gemma 2 9B ITgoogle · Gemma license | 1,203.6 | 1,211.2 | 3.77 | 54,611 | overall | 2026-11-09 | |
| #322 | GPT-4 (0314)openai · Proprietary | 1,201.29 | 1,210.74 | 5.82 | 54,173 | overall | 2026-11-09 | |
| #323 | Command R+cohere · CC-BY-NC-4.0 | 1,199.56 | 1,208.12 | 4.77 | 77,554 | overall | 2026-11-09 | |
| #324 | Qwen2-72B-Instructalibaba · Qianwen LICENSE | 1,198.38 | 1,208.18 | 6.25 | 37,325 | overall | 2026-11-09 | |
| #325 | Hunyuan Standard 256Ktencent · Proprietary | 1,190.38 | 1,213.49 | 34.76 | 2,728 | overall | 2026-11-09 | |
| #326 | Claude 3 Haiku (20240307)anthropic · Proprietary | 1,190.95 | 1,198.42 | 3.63 | 117,701 | overall | 2026-11-09 | |
| #327 | Llama 3.1 Tulu 3 8Ballenai · Llama 3.1 | 1,182.82 | 1,203.81 | 28.66 | 2,896 | overall | 2026-11-09 | |
| #328 | DeepSeek-Coder-V2deepseek · DeepSeek License | 1,184.86 | 1,197.53 | 10.45 | 15,147 | overall | 2026-11-09 | |
| #329 | Ministral 8B (2410)mistral · MRL | 1,181.95 | 1,199.9 | 20.95 | 4,781 | overall | 2026-11-09 | |
| #330 | Command R (08-2024)cohere · CC-BY-NC-4.0 | 1,180.85 | 1,193.89 | 11.06 | 10,140 | overall | 2026-11-09 | |
| #331 | Jamba 1.5 MiniJamba Open | 1,179.52 | 1,193.84 | 13.35 | 8,858 | overall | 2026-11-09 | |
| #332 | Llama 3.1 8B Instructmeta · Llama 3.1 Community | 1,182.48 | 1,190.69 | 4.38 | 49,605 | overall | 2026-11-09 | |
| #333 | GPT-4 (0613)openai · Proprietary | 1,181.99 | 1,190.04 | 4.22 | 88,723 | overall | 2026-11-09 | |
| #334 | Aya Expanse 8Bcohere · CC-BY-NC-4.0 | 1,178.2 | 1,192.04 | 12.46 | 9,818 | overall | 2026-11-09 | |
| #335 | Mistral Large (2402)mistral · Proprietary | 1,171.8 | 1,181.17 | 5.71 | 62,436 | overall | 2026-11-09 | |
| #336 | Qwen1.5-110B-Chatalibaba · Qianwen LICENSE | 1,169.07 | 1,180.09 | 7.9 | 26,195 | overall | 2026-11-09 | |
| #337 | Yi 1.5 34B ChatApache-2.0 | 1,167.97 | 1,177.96 | 6.5 | 24,146 | overall | 2026-11-09 | |
| #338 | Reka Flash 21B (Online, 20240226)Proprietary | 1,163.14 | 1,177.74 | 13.88 | 15,450 | overall | 2026-11-09 | |
| #339 | Qwen1.5-72B-Chatalibaba · Qianwen LICENSE | 1,160.98 | 1,171.34 | 6.99 | 39,302 | overall | 2026-11-09 | |
| #340 | Llama 3 8B Instructmeta · Llama 3 Community | 1,161.9 | 1,169.33 | 3.59 | 104,642 | overall | 2026-11-09 | |
| #341 | Mistral Mediummistral · Proprietary | 1,159.73 | 1,170.56 | 7.64 | 34,550 | overall | 2026-11-09 | |
| #342 | Reka Flash 21B (20240226)Proprietary | 1,159.11 | 1,170.88 | 9.03 | 24,806 | overall | 2026-11-09 | |
| #343 | Command Rcohere · CC-BY-NC-4.0 | 1,158.41 | 1,167.87 | 5.82 | 54,036 | overall | 2026-11-09 | |
| #344 | Mixtral 8x22B Instruct v0.1mistral · Apache 2.0 | 1,157.48 | 1,166.51 | 5.31 | 51,416 | overall | 2026-11-09 | |
| #345 | QwQ-32B-Previewalibaba · Apache 2.0 | 1,150.47 | 1,173.13 | 33.4 | 3,231 | overall | 2026-11-09 | |
| #346 | InternLM2.5 20B ChatOther | 1,151.4 | 1,165.5 | 12.94 | 9,901 | overall | 2026-11-09 | |
| #347 | Gemma 2 2B ITgoogle · Gemma license | 1,151.74 | 1,159.83 | 4.26 | 46,616 | overall | 2026-11-09 | |
| #348 | Granite 3.1 8B Instructibm · Apache 2.0 | 1,138.61 | 1,160.45 | 31.05 | 3,090 | overall | 2026-11-09 | |
| #349 | Gemini Pro (Dev API)google · Proprietary | 1,141.66 | 1,156.05 | 13.46 | 18,354 | overall | 2026-11-09 | |
| #350 | Zephyr ORPO 141B A35B v0.1Apache 2.0 | 1,132.99 | 1,154.41 | 29.86 | 4,652 | overall | 2026-11-09 | |
| #351 | Phi-3 Medium 4K Instructmicrosoft · MIT | 1,132.44 | 1,142.68 | 6.82 | 25,055 | overall | 2026-11-09 | |
| #352 | Qwen1.5-32B-Chatalibaba · Qianwen LICENSE | 1,131.14 | 1,143.28 | 9.59 | 21,741 | overall | 2026-11-09 | |
| #353 | Starling LM 7B BetaApache-2.0 | 1,124.77 | 1,139.33 | 13.79 | 16,056 | overall | 2026-11-09 | |
| #354 | Mixtral 8x7B Instruct v0.1mistral · Apache 2.0 | 1,127.34 | 1,135.79 | 4.65 | 73,503 | overall | 2026-11-09 | |
| #355 | Gemini Progoogle · Proprietary | 1,119.13 | 1,141.96 | 33.95 | 6,390 | overall | 2026-11-09 | |
| #356 | Yi 34B ChatYi License | 1,121.71 | 1,135.24 | 11.92 | 15,483 | overall | 2026-11-09 | |
| #357 | Qwen1.5-14B-Chatalibaba · Qianwen LICENSE | 1,120.67 | 1,134.73 | 12.87 | 17,839 | overall | 2026-11-09 | |
| #358 | Granite 3.1 2B Instructibm · Apache 2.0 | 1,116.38 | 1,138.45 | 31.7 | 3,188 | overall | 2026-11-09 | |
| #359 | GPT-3.5 Turbo (0125)openai · Proprietary | 1,120.26 | 1,129.59 | 5.66 | 66,207 | overall | 2026-11-09 | |
| #360 | Tulu 2 DPO 70BAI2 ImpACT Low-risk | 1,111.36 | 1,130.72 | 24.4 | 6,535 | overall | 2026-11-09 | |
| #361 | WizardLM 70Bmicrosoft · Llama 2 Community | 1,110.2 | 1,128.85 | 22.63 | 8,214 | overall | 2026-11-09 | |
| #362 | DBRX Instruct PreviewDBRX LICENSE | 1,112.83 | 1,124.92 | 9.52 | 32,191 | overall | 2026-11-09 | |
| #363 | Llama 2 70B Chatmeta · Llama 2 Community | 1,109.79 | 1,120.68 | 7.72 | 38,492 | overall | 2026-11-09 | |
| #364 | Nous Hermes 2 Mixtral 8x7B DPOApache-2.0 | 1,100.27 | 1,123.82 | 36.1 | 3,777 | overall | 2026-11-09 | |
| #365 | Phi-3 Small 8K Instructmicrosoft · MIT | 1,103.99 | 1,115.67 | 8.89 | 17,766 | overall | 2026-11-09 | |
| #366 | Llama 3.2 3B Instructmeta · Llama 3.2 | 1,101.99 | 1,117.09 | 14.84 | 7,936 | overall | 2026-11-09 | |
| #367 | Starling LM 7B AlphaCC-BY-NC-4.0 | 1,099.76 | 1,115.57 | 16.26 | 10,224 | overall | 2026-11-09 | |
| #368 | OpenChat 3.5 (0106)Apache-2.0 | 1,098.72 | 1,114.51 | 16.22 | 12,637 | overall | 2026-11-09 | |
| #369 | Vicuna 33BNon-commercial | 1,099.16 | 1,111.37 | 9.71 | 22,479 | overall | 2026-11-09 | |
| #370 | DeepSeek LLM 67B Chatdeepseek · DeepSeek License | 1,093.51 | 1,116.56 | 34.58 | 4,932 | overall | 2026-11-09 | |
| #371 | Snowflake Arctic InstructApache 2.0 | 1,095.1 | 1,106.86 | 8.99 | 32,832 | overall | 2026-11-09 | |
| #372 | Llama 2 70B SteerLM Chatnvidia · Llama 2 Community | 1,085.65 | 1,110.54 | 40.3 | 3,585 | overall | 2026-11-09 | |
| #373 | OpenChat 3.5Apache-2.0 | 1,087.42 | 1,106.65 | 24.07 | 7,968 | overall | 2026-11-09 | |
| #374 | Granite 3.0 8B Instructibm · Apache 2.0 | 1,087.92 | 1,104.98 | 18.95 | 6,638 | overall | 2026-11-09 | |
| #375 | GPT-3.5 Turbo (1106)openai · Proprietary | 1,085.41 | 1,102.84 | 19.77 | 16,619 | overall | 2026-11-09 | |
| #376 | Gemma 1.1 7B ITgoogle · Gemma license | 1,087.98 | 1,099.98 | 9.36 | 23,893 | overall | 2026-11-09 | |
| #377 | OpenHermes 2.5 Mistral 7BApache-2.0 | 1,082.2 | 1,102.81 | 27.66 | 5,006 | overall | 2026-11-09 | |
| #378 | Mistral 7B Instruct v0.2mistral · Apache-2.0 | 1,083.04 | 1,096.11 | 11.12 | 19,402 | overall | 2026-11-09 | |
| #379 | Llama 2 13B Chatmeta · Llama 2 Community | 1,077.81 | 1,091.11 | 11.52 | 19,174 | overall | 2026-11-09 | |
| #380 | Qwen1.5-7B-Chatalibaba · Qianwen LICENSE | 1,073.78 | 1,093.15 | 24.43 | 4,737 | overall | 2026-11-09 | |
| #381 | SOLAR 10.7B Instruct v1.0upstage · CC-BY-NC-4.0 | 1,070.05 | 1,096.13 | 44.25 | 4,155 | overall | 2026-11-09 | |
| #382 | Dolphin 2.2.1 Mistral 7BApache-2.0 | 1,065.7 | 1,096.25 | 60.74 | 1,679 | overall | 2026-11-09 | |
| #383 | Phi-3 Mini 4K Instruct (June 2024)microsoft · MIT | 1,073.62 | 1,086.3 | 10.47 | 12,297 | overall | 2026-11-09 | |
| #384 | Granite 3.0 2B Instructibm · Apache 2.0 | 1,071.65 | 1,088.05 | 17.5 | 6,837 | overall | 2026-11-09 | |
| #385 | WizardLM 13Bmicrosoft · Llama 2 Community | 1,067.33 | 1,085.76 | 22.1 | 7,044 | overall | 2026-11-09 | |
| #386 | Phi-3 Mini 4K Instructmicrosoft · MIT | 1,067.02 | 1,079.61 | 10.31 | 20,118 | overall | 2026-11-09 | |
| #387 | Zephyr 7B BetaMIT | 1,060.74 | 1,078.12 | 19.66 | 11,118 | overall | 2026-11-09 | |
| #388 | MPT 30B ChatCC-BY-NC-SA-4.0 | 1,056.53 | 1,080.7 | 38.04 | 2,572 | overall | 2026-11-09 | |
| #389 | Code Llama 34B Instructmeta · Llama 2 Community | 1,056.73 | 1,074.25 | 19.96 | 7,366 | overall | 2026-11-09 | |
| #390 | Zephyr 7B AlphaMIT | 1,042.73 | 1,074.02 | 63.73 | 1,785 | overall | 2026-11-09 | |
| #391 | Vicuna 13BLlama 2 Community | 1,051.08 | 1,064.24 | 11.27 | 19,367 | overall | 2026-11-09 | |
| #392 | Code Llama 70B Instructmeta · Llama 2 Community | 1,039.28 | 1,075.22 | 84.06 | 1,143 | overall | 2026-11-09 | |
| #393 | Gemma 7B ITgoogle · Gemma license | 1,046.64 | 1,065.68 | 23.59 | 8,925 | overall | 2026-11-09 | |
| #394 | Llama 3.2 1B Instructmeta · Llama 3.2 | 1,046.95 | 1,062.34 | 15.41 | 8,045 | overall | 2026-11-09 | |
| #395 | Falcon 180B ChatFalcon-180B TII License | 1,037.37 | 1,071.35 | 75.13 | 1,295 | overall | 2026-11-09 | |
| #396 | Llama 2 7B Chatmeta · Llama 2 Community | 1,046.44 | 1,060.36 | 12.61 | 14,148 | overall | 2026-11-09 | |
| #397 | Guanaco 33BNon-commercial | 1,041.4 | 1,065.37 | 37.39 | 2,921 | overall | 2026-11-09 | |
| #398 | Qwen-14B-Chatalibaba · Qianwen LICENSE | 1,040.18 | 1,061.89 | 30.68 | 4,964 | overall | 2026-11-09 | |
| #399 | Phi-3 Mini 128K Instructmicrosoft · MIT | 1,043.18 | 1,057.61 | 13.55 | 20,685 | overall | 2026-11-09 | |
| #400 | SmolLM2 1.7B InstructApache 2.0 | 1,027.96 | 1,056.09 | 51.49 | 2,199 | overall | 2026-11-09 | |
| #401 | StripedHyena Nous 7BApache 2.0 | 1,027.51 | 1,049.38 | 31.12 | 5,182 | overall | 2026-11-09 | |
| #402 | OLMo 7B Instructallenai · Apache-2.0 | 1,020.79 | 1,042.84 | 31.65 | 6,328 | overall | 2026-11-09 | |
| #403 | Vicuna 7BLlama 2 Community | 1,021.89 | 1,040.02 | 21.39 | 6,923 | overall | 2026-11-09 | |
| #404 | PaLM 2google · Proprietary | 1,018.05 | 1,036.44 | 22.01 | 8,554 | overall | 2026-11-09 | |
| #405 | Mistral 7B Instructmistral · Apache 2.0 | 1,014.36 | 1,032.67 | 21.83 | 8,977 | overall | 2026-11-09 | |
| #406 | Gemma 1.1 2B ITgoogle · Gemma license | 1,014.56 | 1,029.89 | 15.29 | 10,854 | overall | 2026-11-09 | |
| #407 | Gemma 2B ITgoogle · Gemma license | 990.69 | 1,013.62 | 34.22 | 4,780 | overall | 2026-11-09 | |
| #408 | Qwen1.5-4B-Chatalibaba · Qianwen LICENSE | 988.03 | 1,006.45 | 22.08 | 7,597 | overall | 2026-11-09 | |
| #409 | Koala 13BNon-commercial | 979.94 | 999.29 | 24.37 | 6,965 | overall | 2026-11-09 | |
| #410 | ChatGLM3 6BApache-2.0 | 960.49 | 983.59 | 34.71 | 4,658 | overall | 2026-11-09 | |
| #411 | GPT4All 13B SnoozyNon-commercial | 941.19 | 971.17 | 58.49 | 1,743 | overall | 2026-11-09 | |
| #412 | MPT 7B ChatCC-BY-NC-SA-4.0 | 943.52 | 966.93 | 35.66 | 3,924 | overall | 2026-11-09 | |
| #413 | RWKV-4 Raven 14BApache 2.0 | 937.16 | 959.61 | 32.8 | 4,845 | overall | 2026-11-09 | |
| #414 | ChatGLM2 6BApache-2.0 | 925.2 | 952.06 | 46.94 | 2,658 | overall | 2026-11-09 | |
| #415 | Alpaca 13BNon-commercial | 921.57 | 944.06 | 32.91 | 5,745 | overall | 2026-11-09 | |
| #416 | ChatGLM 6BNon-commercial | 906.26 | 930.68 | 38.8 | 4,914 | overall | 2026-11-09 | |
| #417 | OpenAssistant Pythia 12BApache 2.0 | 905.4 | 926.74 | 29.63 | 6,310 | overall | 2026-11-09 | |
| #418 | FastChat-T5 3BApache 2.0 | 882.21 | 906.59 | 38.69 | 4,203 | overall | 2026-11-09 | |
| #419 | StableLM Tuned Alpha 7BCC-BY-NC-SA-4.0 | 854.04 | 879.11 | 40.93 | 3,287 | overall | 2026-11-09 | |
| #420 | Dolly 2.0 12BMIT | 837.91 | 864.35 | 45.52 | 3,412 | overall | 2026-11-09 | |
| #421 | LLaMA 13Bmeta · Non-commercial | 817.99 | 849.04 | 62.75 | 2,391 | overall | 2026-11-09 |
Evaluates coding agents on 113 long-horizon, real-world software engineering tasks written from scratch. Compares Pass@1 accuracy against actual cost and step counts while avoiding training contamination.
Opens in a new tabIndependent benchmarks rather than provider-reported results. Its Intelligence Index covers reasoning, coding, science and knowledge alongside speed, pricing and context window metrics.
Opens in a new tabNew questions every month help prevent contamination. Automated, objective grading with unique correct answers focuses on mathematics, coding, reasoning and data analysis; widely recognized in academia.
Opens in a new tabOriginal Chinese questions tailored to Chinese language, policy and culture, covering six capabilities including mathematical reasoning, coding, hallucination control and agent planning.
Opens in a new tabCreated by Shanghai AI Laboratory with over 20 companies, spanning five capability dimensions and 70+ datasets for Chinese and English models, plus human voting in Compass Arena.