LOADINGLoading
167 models
| Rank | Model | Rating | Rating lower bound | Rating upper bound | Variance | Votes | Category | Source updated |
|---|---|---|---|---|---|---|---|---|
| #1 | Claude Fable 5 (High)anthropic · Proprietary | 1,318.72 | 1,332.47 | 12.3 | 15,536 | overall | 2026-11-09 | |
| #2 | Claude Opus 5.5 (High)anthropic · Proprietary | 1,313.97 | 1,333.63 | 25.16 | 4,789 | overall | 2026-11-09 | |
| #3 | Claude Fable 5.1 (Max)anthropic · Proprietary | 1,313.03 | 1,330.21 | 19.21 | 6,296 | overall | 2026-11-09 | |
| #4 | Claude Opus 4.7anthropic · Proprietary | 1,312.18 | 1,325.25 | 11.12 | 23,777 | overall | 2026-11-09 | |
| #5 | Claude Opus 5 (High)anthropic · Proprietary | 1,311.02 | 1,323.94 | 10.87 | 19,345 | overall | 2026-11-09 | |
| #6 | Gemini 3.8 Flash (High)google · Proprietary | 1,308.62 | 1,324.94 | 17.33 | 7,624 | overall | 2026-11-09 | |
| #7 | Claude Opus 4.6 (High)anthropic · Proprietary | 1,309.24 | 1,321.91 | 10.44 | 22,116 | overall | 2026-11-09 | |
| #8 | Claude Opus 4.7 (High)anthropic · Proprietary | 1,307.44 | 1,320.45 | 11.02 | 22,609 | overall | 2026-11-09 | |
| #9 | Gemini 3.7 Flash (High)google · Proprietary | 1,304.65 | 1,321.63 | 18.77 | 6,840 | overall | 2026-11-09 | |
| #10 | Claude Opus 4.6anthropic · Proprietary | 1,306.01 | 1,318.42 | 10.01 | 26,627 | overall | 2026-11-09 | |
| #11 | Qwen3.8-Maxalibaba · Proprietary | 1,304.57 | 1,319.45 | 14.41 | 9,842 | overall | 2026-11-09 | |
| #12 | Muse Spark 1.3 (Max)meta · Proprietary | 1,301.48 | 1,317.65 | 17.01 | 7,683 | overall | 2026-11-09 | |
| #13 | Gemini 3.5 Flash (High)google · Proprietary | 1,300.95 | 1,314.15 | 11.34 | 15,325 | overall | 2026-11-09 | |
| #14 | Muse Sparkmeta · Proprietary | 1,296.96 | 1,315.04 | 21.26 | 5,843 | overall | 2026-11-09 | |
| #15 | Gemini 3.5 Flash (Medium)google · Proprietary | 1,298.89 | 1,312.1 | 11.36 | 15,418 | overall | 2026-11-09 | |
| #16 | Muse Spark 1.2 (xHigh)meta · Proprietary | 1,290.56 | 1,319.3 | 53.75 | 1,930 | overall | 2026-11-09 | |
| #17 | Gemini 3 Progoogle · Proprietary | 1,297.56 | 1,312.27 | 14.1 | 13,547 | overall | 2026-11-09 | |
| #18 | Muse Spark 1.3 (xHigh)meta · Proprietary | 1,292.6 | 1,309.01 | 17.51 | 7,522 | overall | 2026-11-09 | |
| #19 | GPT-5.4 (High)openai · Proprietary | 1,295.18 | 1,306.33 | 8.1 | 32,045 | overall | 2026-11-09 | |
| #20 | Gemini 3.6 Flash (High)google · Proprietary | 1,289.17 | 1,304.21 | 14.72 | 10,352 | overall | 2026-11-09 | |
| #21 | Gemini 3.1 Pro Previewgoogle · Proprietary | 1,291.03 | 1,301.04 | 6.52 | 48,242 | overall | 2026-11-09 | |
| #22 | GPT-5.5openai · Proprietary | 1,290.21 | 1,301.46 | 8.24 | 30,058 | overall | 2026-11-09 | |
| #23 | Claude Opus 4.8 (High)anthropic · Proprietary | 1,288.31 | 1,301.15 | 10.72 | 18,178 | overall | 2026-11-09 | |
| #24 | GLM-5.3-Flashzai · MIT | 1,289.18 | 1,300.21 | 7.92 | 31,530 | overall | 2026-11-09 | |
| #25 | GPT-5.5 (High)openai · Proprietary | 1,288.84 | 1,300.23 | 8.45 | 28,348 | overall | 2026-11-09 | |
| #26 | Muse Spark 1.1meta · Proprietary | 1,284.95 | 1,298.52 | 11.98 | 13,413 | overall | 2026-11-09 | |
| #27 | GPT-5.4openai · Proprietary | 1,285.31 | 1,298.14 | 10.71 | 22,608 | overall | 2026-11-09 | |
| #28 | Claude Opus 4.8anthropic · Proprietary | 1,282.17 | 1,295.08 | 10.84 | 18,692 | overall | 2026-11-09 | |
| #29 | Grok 4.5xai · Proprietary | 1,281.19 | 1,294.84 | 12.13 | 13,991 | overall | 2026-11-09 | |
| #30 | GPT-6.1 Sol (Max)openai · Proprietary | 1,275.48 | 1,296.4 | 28.47 | 3,987 | overall | 2026-11-09 | |
| #31 | Gemini 3 Flashgoogle · Proprietary | 1,279.49 | 1,289.79 | 6.9 | 38,830 | overall | 2026-11-09 | |
| #32 | Claude Sonnet 5.5 (xHigh)anthropic · Proprietary | 1,274.08 | 1,294.44 | 26.97 | 4,257 | overall | 2026-11-09 | |
| #33 | Claude Sonnet 4.6anthropic · Proprietary | 1,276.59 | 1,288.72 | 9.57 | 27,201 | overall | 2026-11-09 | |
| #34 | Kimi K2.6moonshot · Modified MIT | 1,275.69 | 1,289.16 | 11.81 | 16,265 | overall | 2026-11-09 | |
| #35 | GPT-5.6 Sol (xHigh)openai · Proprietary | 1,275.07 | 1,289.31 | 13.21 | 12,342 | overall | 2026-11-09 | |
| #36 | Gemma 4 31Bgoogle · Apache 2.0 | 1,273.88 | 1,284.89 | 7.89 | 41,787 | overall | 2026-11-09 | |
| #37 | DeepSeek-V4.1-Flash-20260910 (Max)deepseek · MIT | 1,269.07 | 1,289.24 | 26.47 | 4,247 | overall | 2026-11-09 | |
| #38 | GPT-6 Astra (Max)openai · Proprietary | 1,269.4 | 1,287.64 | 21.65 | 5,517 | overall | 2026-11-09 | |
| #39 | Qwen3.7-Plusalibaba · Proprietary | 1,270.74 | 1,283.77 | 11.06 | 15,152 | overall | 2026-11-09 | |
| #40 | Dola Seed 2.0 Probytedance · Proprietary | 1,266.98 | 1,281.28 | 13.3 | 10,929 | overall | 2026-11-09 | |
| #41 | Claude Sonnet 5 (High)anthropic · Proprietary | 1,264.93 | 1,278.32 | 11.67 | 14,778 | overall | 2026-11-09 | |
| #42 | Qwen3.8-27Balibaba · Apache 2.0 | 1,262.09 | 1,277.15 | 14.77 | 9,632 | overall | 2026-11-09 | |
| #43 | GPT-5.6 Terra (xHigh)openai · Proprietary | 1,262.09 | 1,276.06 | 12.71 | 13,243 | overall | 2026-11-09 | |
| #44 | Kimi K2.5 (Thinking)moonshot · Modified MIT | 1,263.24 | 1,274.46 | 8.18 | 28,014 | overall | 2026-11-09 | |
| #45 | Gemini 3.5 Flash-Litegoogle · Proprietary | 1,260.53 | 1,275.44 | 14.47 | 10,800 | overall | 2026-11-09 | |
| #46 | GPT-5.2 Chat (20260210)openai · Proprietary | 1,261.25 | 1,274.12 | 10.77 | 16,361 | overall | 2026-11-09 | |
| #47 | MiMo-V2.6-Proxiaomi · MIT | 1,251.36 | 1,280.41 | 54.94 | 1,826 | overall | 2026-11-09 | |
| #48 | GLM-5V-Turbozai · Proprietary | 1,260.35 | 1,271 | 7.37 | 43,637 | overall | 2026-11-09 | |
| #49 | Gemini 3 Flash (Minimal)google · Proprietary | 1,260.1 | 1,270.62 | 7.2 | 36,907 | overall | 2026-11-09 | |
| #50 | Grok 4.6 (High)xai · Proprietary | 1,256.12 | 1,271.87 | 16.16 | 8,666 | overall | 2026-11-09 | |
| #51 | Gemini 2.5 Progoogle · Proprietary | 1,258.74 | 1,267.74 | 5.27 | 88,553 | overall | 2026-11-09 | |
| #52 | Step 5 Previewstepfun · Proprietary | 1,252.28 | 1,274.11 | 31.02 | 3,523 | overall | 2026-11-09 | |
| #53 | Grok 4.20 Beta (Reasoning, 0309)xai · Proprietary | 1,256.86 | 1,268.88 | 9.4 | 26,586 | overall | 2026-11-09 | |
| #54 | Qwen3.5-397B-A17Balibaba · Apache 2.0 | 1,257.19 | 1,267.56 | 6.99 | 33,611 | overall | 2026-11-09 | |
| #55 | Gemma 4 26B A4Bgoogle · Apache 2.0 | 1,253.32 | 1,266.09 | 10.61 | 23,747 | overall | 2026-11-09 | |
| #56 | MiMo-V2.6-Flashxiaomi · MIT | 1,251.02 | 1,268.1 | 18.98 | 6,906 | overall | 2026-11-09 | |
| #57 | Grok 4.20 Multi-Agent Beta (0309)xai · Proprietary | 1,253.12 | 1,265.21 | 9.53 | 24,357 | overall | 2026-11-09 | |
| #58 | GPT-5.6 Luna (xHigh)openai · Proprietary | 1,248.48 | 1,263.16 | 14.02 | 11,071 | overall | 2026-11-09 | |
| #59 | Gemini 2.5 Flash Preview (09-2025)google · Proprietary | 1,243.41 | 1,262.83 | 24.54 | 4,780 | overall | 2026-11-09 | |
| #60 | Kimi K2.5 (Instant)moonshot · Modified MIT | 1,242.33 | 1,263.59 | 29.41 | 4,093 | overall | 2026-11-09 | |
| #61 | GPT-5.5 Instantopenai · Proprietary | 1,241.98 | 1,259.07 | 19 | 7,567 | overall | 2026-11-09 | |
| #62 | MiniMax-M3minimax · MiniMax Community License | 1,242.96 | 1,255.35 | 9.99 | 21,159 | overall | 2026-11-09 | |
| #63 | GPT-5.1 (High)openai · Proprietary | 1,241.35 | 1,256.88 | 15.7 | 9,794 | overall | 2026-11-09 | |
| #64 | ERNIE-5.0-Preview (1220)baidu · Proprietary | 1,237.08 | 1,259.35 | 32.27 | 3,334 | overall | 2026-11-09 | |
| #65 | MiMo-V2.5xiaomi · MIT | 1,241.75 | 1,253.28 | 8.65 | 29,427 | overall | 2026-11-09 | |
| #66 | Qwen3-VL-235B-A22B-Instructalibaba · Apache 2.0 | 1,239.7 | 1,253.54 | 12.46 | 12,672 | overall | 2026-11-09 | |
| #67 | GPT-5.2 (High)openai · Proprietary | 1,239.46 | 1,251.45 | 9.35 | 18,920 | overall | 2026-11-09 | |
| #68 | GPT-5.4 mini (High)openai · Proprietary | 1,238.29 | 1,250.55 | 9.77 | 25,535 | overall | 2026-11-09 | |
| #69 | Qwen3.5-122B-A10Balibaba · Apache 2.0 | 1,237.5 | 1,250.94 | 11.74 | 13,171 | overall | 2026-11-09 | |
| #70 | Mistral Large 4mistral · Modified MIT | 1,229.95 | 1,258.05 | 51.4 | 2,093 | overall | 2026-11-09 | |
| #71 | ChatGPT-4o Latest (20250326)openai · Proprietary | 1,237.79 | 1,248.75 | 7.81 | 23,331 | overall | 2026-11-09 | |
| #72 | Gemini 3.1 Flash-Lite Previewgoogle · Proprietary | 1,234.59 | 1,245.97 | 8.43 | 27,443 | overall | 2026-11-09 | |
| #73 | Qwen3.5-27Balibaba · Apache 2.0 | 1,234.27 | 1,245.01 | 7.51 | 31,308 | overall | 2026-11-09 | |
| #74 | Inkling-Smallthinky · Apache 2.0 | 1,228.07 | 1,243.66 | 15.82 | 9,259 | overall | 2026-11-09 | |
| #75 | Gemini 2.5 Flashgoogle · Proprietary | 1,230.8 | 1,239.8 | 5.28 | 59,919 | overall | 2026-11-09 | |
| #76 | GPT-5.1openai · Proprietary | 1,227.46 | 1,242.45 | 14.62 | 10,753 | overall | 2026-11-09 | |
| #77 | GPT-6 Sol (Max)openai · Proprietary | 1,223.03 | 1,242.26 | 24.06 | 5,018 | overall | 2026-11-09 | |
| #78 | GPT-5 Chatopenai · Proprietary | 1,224.64 | 1,238.7 | 12.88 | 39,843 | overall | 2026-11-09 | |
| #79 | Grok 4.7 (xHigh)xai · Proprietary | 1,221.17 | 1,238.87 | 20.39 | 6,181 | overall | 2026-11-09 | |
| #80 | GPT-5.2openai · Proprietary | 1,222.92 | 1,234.75 | 9.12 | 20,001 | overall | 2026-11-09 | |
| #81 | Grok 4.3xai · Proprietary | 1,222.95 | 1,234.32 | 8.42 | 29,224 | overall | 2026-11-09 | |
| #82 | MiMo-V2-Omnixiaomi · Proprietary | 1,220.7 | 1,235.27 | 13.82 | 10,599 | overall | 2026-11-09 | |
| #83 | Mistral Medium 3.5mistral · Modified MIT | 1,212.93 | 1,231.89 | 23.39 | 5,330 | overall | 2026-11-09 | |
| #84 | Mistral Large 3mistral · Apache 2.0 | 1,214.26 | 1,229.32 | 14.76 | 10,142 | overall | 2026-11-09 | |
| #85 | NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)nvidia · OpenMDW-1.1 | 1,205.11 | 1,223.73 | 22.57 | 5,532 | overall | 2026-11-09 | |
| #86 | o3 (2025-04-16)openai · Proprietary | 1,207.2 | 1,220.27 | 11.11 | 45,507 | overall | 2026-11-09 | |
| #87 | Qwen-VL-Max (2025-08-13)alibaba · Proprietary | 1,200.36 | 1,224.35 | 37.47 | 3,159 | overall | 2026-11-09 | |
| #88 | GPT-6 Luna (Max)openai · Proprietary | 1,202.3 | 1,220.07 | 20.56 | 6,202 | overall | 2026-11-09 | |
| #89 | Grok 4 (0709)xai · Proprietary | 1,203.02 | 1,217.59 | 13.82 | 30,130 | overall | 2026-11-09 | |
| #90 | GPT-4.1 (2025-04-14)openai · Proprietary | 1,203.52 | 1,216.88 | 11.61 | 40,946 | overall | 2026-11-09 | |
| #91 | GPT-5 (High)openai · Proprietary | 1,201.22 | 1,214.81 | 12.01 | 34,378 | overall | 2026-11-09 | |
| #92 | Qwen3-VL-235B-A22B-Thinkingalibaba · Apache 2.0 | 1,194.01 | 1,218.53 | 39.12 | 2,379 | overall | 2026-11-09 | |
| #93 | GPT-5 mini (High)openai · Proprietary | 1,194.66 | 1,210.28 | 15.87 | 28,904 | overall | 2026-11-09 | |
| #94 | Grok 4.1 Fast (Reasoning)xai · Proprietary | 1,194.45 | 1,208.17 | 12.26 | 13,295 | overall | 2026-11-09 | |
| #95 | Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)google · Proprietary | 1,188.62 | 1,207.6 | 23.44 | 4,849 | overall | 2026-11-09 | |
| #96 | GPT-5.4 nano (High)openai · Proprietary | 1,189.29 | 1,201.79 | 10.17 | 25,407 | overall | 2026-11-09 | |
| #97 | GPT-4.5 Preview (2025-02-27)openai · Proprietary | 1,183.05 | 1,206.51 | 35.84 | 2,925 | overall | 2026-11-09 | |
| #98 | o4-mini (2025-04-16)openai · Proprietary | 1,186.9 | 1,201.02 | 12.99 | 41,276 | overall | 2026-11-09 | |
| #99 | Claude Opus 4 (Thinking 16K, 20250514)anthropic · Proprietary | 1,175.94 | 1,207.92 | 66.56 | 1,287 | overall | 2026-11-09 | |
| #100 | Claude Sonnet 4 (Thinking 32K, 20250514)anthropic · Proprietary | 1,173.83 | 1,207.75 | 74.91 | 1,141 | overall | 2026-11-09 | |
| #101 | Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)google · Proprietary | 1,179.88 | 1,194.68 | 14.26 | 35,868 | overall | 2026-11-09 | |
| #102 | Step-1o Turbo (202506)stepfun · Proprietary | 1,171.39 | 1,199.79 | 52.48 | 1,895 | overall | 2026-11-09 | |
| #103 | GPT-4.1 mini (2025-04-14)openai · Proprietary | 1,173.77 | 1,188.72 | 14.55 | 40,154 | overall | 2026-11-09 | |
| #104 | Hunyuan Large Visiontencent · Proprietary | 1,163.39 | 1,196.15 | 69.83 | 1,271 | overall | 2026-11-09 | |
| #105 | Hunyuan Vision 1.5 Thinkingtencent · Proprietary | 1,166.8 | 1,191.07 | 38.33 | 2,418 | overall | 2026-11-09 | |
| #106 | Step-3stepfun · Apache 2.0 | 1,164.26 | 1,187.71 | 35.8 | 3,185 | overall | 2026-11-09 | |
| #107 | Claude Opus 4 (20250514)anthropic · Proprietary | 1,162.31 | 1,188.18 | 43.58 | 2,166 | overall | 2026-11-09 | |
| #108 | Claude Sonnet 4 (20250514)anthropic · Proprietary | 1,161.12 | 1,189.16 | 51.15 | 1,803 | overall | 2026-11-09 | |
| #109 | Mistral Medium 3.1 (2508)mistral · Proprietary | 1,166.2 | 1,178.49 | 9.83 | 41,518 | overall | 2026-11-09 | |
| #110 | Claude 3.7 Sonnet (Thinking 32K, 20250219)anthropic · Proprietary | 1,152.92 | 1,184.02 | 62.94 | 1,432 | overall | 2026-11-09 | |
| #111 | o1 (2024-12-17)openai · Proprietary | 1,157.46 | 1,179.05 | 30.34 | 3,694 | overall | 2026-11-09 | |
| #112 | Gemma 3 27B ITgoogle · Gemma | 1,156.32 | 1,172.38 | 16.77 | 16,943 | overall | 2026-11-09 | |
| #113 | GLM-4.6Vzai · MIT | 1,149.41 | 1,176.81 | 48.87 | 2,440 | overall | 2026-11-09 | |
| #114 | Gemini 1.5 Pro (002)google · Proprietary | 1,152.2 | 1,170.38 | 21.5 | 8,902 | overall | 2026-11-09 | |
| #115 | GPT-5 nano (High)openai · Proprietary | 1,148.01 | 1,170.1 | 31.76 | 3,921 | overall | 2026-11-09 | |
| #116 | Gemini 2.0 Flash (001)google · Proprietary | 1,150.51 | 1,164.93 | 13.54 | 10,123 | overall | 2026-11-09 | |
| #117 | Mistral Medium 3 (2505)mistral · Proprietary | 1,148.44 | 1,164.96 | 17.75 | 10,773 | overall | 2026-11-09 | |
| #118 | GLM-4.5Vzai · MIT | 1,142.48 | 1,165.74 | 35.23 | 3,233 | overall | 2026-11-09 | |
| #119 | Qwen2.5-VL-32B-Instructalibaba · Apache 2.0 | 1,136.64 | 1,167.42 | 61.65 | 1,490 | overall | 2026-11-09 | |
| #120 | Claude 3.7 Sonnet (20250219)anthropic · Proprietary | 1,141.37 | 1,160.13 | 22.89 | 4,516 | overall | 2026-11-09 | |
| #121 | Mistral Small 3.2 (2506)mistral · Apache 2.0 | 1,132.54 | 1,150.67 | 21.39 | 10,825 | overall | 2026-11-09 | |
| #122 | Llama 4 Maverick 17B 128E Instructmeta · Llama 4 | 1,132.47 | 1,150.57 | 21.33 | 6,912 | overall | 2026-11-09 | |
| #123 | Gemini 1.5 Flash (002)google · Proprietary | 1,130.56 | 1,150.5 | 25.87 | 7,241 | overall | 2026-11-09 | |
| #124 | GPT-4o (2024-05-13)openai · Proprietary | 1,127.71 | 1,145.32 | 20.17 | 23,273 | overall | 2026-11-09 | |
| #125 | Mistral Small 3.1 24B Instruct (2503)mistral · Apache 2.0 | 1,127.63 | 1,144.57 | 18.66 | 28,452 | overall | 2026-11-09 | |
| #126 | Claude 3.5 Sonnet (20241022)anthropic · Proprietary | 1,117.52 | 1,133.37 | 16.34 | 10,372 | overall | 2026-11-09 | |
| #127 | Step-1o Vision 32K (High Res)stepfun · Proprietary | 1,109.02 | 1,134.38 | 41.86 | 2,833 | overall | 2026-11-09 | |
| #128 | Claude 3.5 Sonnet (20240620)anthropic · Proprietary | 1,110.12 | 1,130.3 | 26.51 | 21,624 | overall | 2026-11-09 | |
| #129 | Llama 4 Scout 17B 16E Instructmeta · Llama | 1,108.93 | 1,127.83 | 23.25 | 6,431 | overall | 2026-11-09 | |
| #130 | Qwen2.5-VL-72B-Instructalibaba · Qwen | 1,096.37 | 1,118.17 | 30.91 | 3,768 | overall | 2026-11-09 | |
| #131 | Gemini 2.0 Flash-Lite Preview (02-05)google · Proprietary | 1,089.75 | 1,110.83 | 28.9 | 3,991 | overall | 2026-11-09 | |
| #132 | Claude 3.5 Haiku (20241022)anthropic · Proprietary | 1,075.86 | 1,107.97 | 67.09 | 1,397 | overall | 2026-11-09 | |
| #133 | GPT-4 Turbo (2024-04-09)openai · Proprietary | 1,078.15 | 1,101.37 | 35.07 | 13,391 | overall | 2026-11-09 | |
| #134 | Pixtral Large (2411)mistral · MRL | 1,079.94 | 1,098.62 | 22.71 | 5,423 | overall | 2026-11-09 | |
| #135 | Gemini 1.5 Pro (001)google · Proprietary | 1,076.5 | 1,099.9 | 35.62 | 16,734 | overall | 2026-11-09 | |
| #136 | Molmo 2 8Ballenai · Apache 2.0 | 1,062 | 1,101.18 | 99.89 | 1,187 | overall | 2026-11-09 | |
| #137 | GPT-4o mini (2024-07-18)openai · Proprietary | 1,057.17 | 1,073.86 | 18.12 | 17,341 | overall | 2026-11-09 | |
| #138 | GPT-4o (2024-08-06)openai · Proprietary | 1,051.94 | 1,076.95 | 40.69 | 3,376 | overall | 2026-11-09 | |
| #139 | GPT-4.1 nano (2025-04-14)openai · Proprietary | 1,044.82 | 1,081.4 | 87.09 | 1,211 | overall | 2026-11-09 | |
| #140 | Qwen-VL-Max (1119)alibaba · Proprietary | 1,041.24 | 1,073.72 | 68.69 | 1,422 | overall | 2026-11-09 | |
| #141 | Qwen2-VL-72Balibaba · Qwen | 1,036.59 | 1,057.08 | 27.31 | 5,937 | overall | 2026-11-09 | |
| #142 | Step-1V 32Kstepfun · Proprietary | 1,029.15 | 1,062.58 | 72.73 | 1,534 | overall | 2026-11-09 | |
| #143 | Gemini 1.5 Flash-8B (001)google · Proprietary | 1,033.33 | 1,054.65 | 29.57 | 6,243 | overall | 2026-11-09 | |
| #144 | Claude 3 Opus (20240229)anthropic · Proprietary | 1,012.45 | 1,033.19 | 28 | 15,565 | overall | 2026-11-09 | |
| #145 | Molmo 72B (0924)allenai · Apache 2.0 | 999.09 | 1,025.31 | 44.77 | 3,048 | overall | 2026-11-09 | |
| #146 | Pixtral 12B (2409)mistral · Apache 2.0 | 998.88 | 1,018.05 | 23.92 | 7,511 | overall | 2026-11-09 | |
| #147 | Gemini 1.5 Flash (001)google · Proprietary | 995.97 | 1,019.74 | 36.77 | 13,260 | overall | 2026-11-09 | |
| #148 | InternVL2 26BMIT | 991.63 | 1,017.31 | 42.92 | 5,148 | overall | 2026-11-09 | |
| #149 | Llama 3.2 90B Vision Instructmeta · Llama 3.2 | 990.27 | 1,008.83 | 22.42 | 8,682 | overall | 2026-11-09 | |
| #150 | Hunyuan Standard Vision (2024-12-31)tencent · Proprietary | 977.6 | 1,020.38 | 119.07 | 809 | overall | 2026-11-09 | |
| #151 | Aya Vision 32Bcohere · CC-BY-NC-4.0 | 973.48 | 1,017.49 | 126.06 | 847 | overall | 2026-11-09 | |
| #152 | Amazon Nova Lite 1.0amazon · Proprietary | 975.32 | 1,005.34 | 58.62 | 1,854 | overall | 2026-11-09 | |
| #153 | Qwen2-VL-7B-Instructalibaba · Apache 2.0 | 979.24 | 1,000.38 | 29.07 | 5,766 | overall | 2026-11-09 | |
| #154 | Claude 3 Sonnet (20240229)anthropic · Proprietary | 972.39 | 995.23 | 33.95 | 12,314 | overall | 2026-11-09 | |
| #155 | Amazon Nova Pro 1.0amazon · Proprietary | 966.44 | 994.23 | 50.24 | 2,335 | overall | 2026-11-09 | |
| #156 | Yi VisionProprietary | 959.49 | 995.77 | 85.64 | 1,219 | overall | 2026-11-09 | |
| #157 | Llama 3.2 11B Vision Instructmeta · Llama 3.2 | 954.93 | 977.63 | 33.55 | 4,817 | overall | 2026-11-09 | |
| #158 | Molmo 7B-D (0924)allenai · Apache 2.0 | 944.78 | 972.43 | 49.74 | 2,815 | overall | 2026-11-09 | |
| #159 | Claude 3 Haiku (20240307)anthropic · Proprietary | 937.51 | 962.58 | 40.89 | 13,380 | overall | 2026-11-09 | |
| #160 | InternVL2 4BMIT | 928.67 | 953.76 | 40.96 | 3,703 | overall | 2026-11-09 | |
| #161 | nvila-internal-15b-v1nvidia · - | 920.16 | 959.93 | 102.91 | 1,077 | overall | 2026-11-09 | |
| #162 | LLaVA 1.6 34BApache 2.0 | 924.08 | 948.61 | 39.16 | 4,531 | overall | 2026-11-09 | |
| #163 | CogVLM2 Llama3 Chat 19Bzai · CogVLM2 | 912.2 | 942.68 | 60.48 | 1,991 | overall | 2026-11-09 | |
| #164 | LLaVA-OneVision Qwen2 72B OVApache 2.0 | 904.72 | 940.73 | 84.37 | 1,321 | overall | 2026-11-09 | |
| #165 | MiniCPM-V 2.6Apache 2.0 | 895.53 | 927.5 | 66.52 | 1,987 | overall | 2026-11-09 | |
| #166 | Phi-3.5 Vision Instructmicrosoft · MIT | 835.58 | 867.16 | 64.91 | 2,592 | overall | 2026-11-09 | |
| #167 | Phi-3 Vision 128K Instructmicrosoft · MIT | 792.9 | 830.33 | 91.17 | 1,401 | 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.
