LOADING加载中
63 个模型
| 排名 | 模型 | 评分 | 评分下界 | 评分上界 | 方差 | 投票数 | 分类 | 源数据更新 |
|---|---|---|---|---|---|---|---|---|
| #1 | GPT-Image-2.5 Sunburstopenai · Proprietary | 1,515.08 | 1,524.54 | 5.82 | 120,359 | overall | 2026-11-09 | |
| #2 | GPT-Image-2.5 Flareopenai · Proprietary | 1,479.92 | 1,489 | 5.36 | 117,429 | overall | 2026-11-09 | |
| #3 | GPT-Image-2.6 Sunburst (Medium)openai · Proprietary | 1,466.17 | 1,487.18 | 28.74 | 3,520 | overall | 2026-11-09 | |
| #4 | MAI-Image-2.7-Previewmicrosoft-ai · Proprietary | 1,462.01 | 1,474.5 | 10.15 | 20,315 | overall | 2026-11-09 | |
| #5 | GPT-Image-2 (Medium)openai · Proprietary | 1,457.89 | 1,463.94 | 2.38 | 355,469 | overall | 2026-11-09 | |
| #6 | GPT-Image-2.6 Flare (Medium)openai · Proprietary | 1,449.71 | 1,470.41 | 27.9 | 3,558 | overall | 2026-11-09 | |
| #7 | Grok Imagine Image 2.0xai · Proprietary | 1,431.18 | 1,442.68 | 8.61 | 34,005 | overall | 2026-11-09 | |
| #8 | MAI-Image-2.6microsoft-ai · Proprietary | 1,423.03 | 1,432.34 | 5.63 | 83,022 | overall | 2026-11-09 | |
| #9 | Gemini Nano Banana 2.1google · Proprietary | 1,421.28 | 1,433.2 | 9.26 | 12,071 | overall | 2026-11-09 | |
| #10 | Grok Imagine Image 2.0 (20260801)xai · Proprietary | 1,413.88 | 1,422.39 | 4.71 | 121,860 | overall | 2026-11-09 | |
| #11 | Krea 3 Ultrakrea | 1,399.9 | 1,422.99 | 34.68 | 2,629 | overall | 2026-11-09 | |
| #12 | MAI-Image-2.5microsoft-ai · Proprietary | 1,396.64 | 1,404.14 | 3.66 | 183,608 | overall | 2026-11-09 | |
| #13 | Muse Imagemeta · Proprietary | 1,395.74 | 1,403.34 | 3.75 | 195,504 | overall | 2026-11-09 | |
| #14 | Seedream 5.0 Probytedance · Proprietary | 1,388.26 | 1,394.65 | 2.66 | 337,529 | overall | 2026-11-09 | |
| #15 | Grok Imagine Image (Quality, 20260519)xai · Proprietary | 1,385.55 | 1,396.84 | 8.29 | 37,154 | overall | 2026-11-09 | |
| #16 | Gemini 3 Pro Image (nano-banana-pro, 2K)google · Proprietary | 1,388.08 | 1,393.16 | 1.68 | 683,438 | overall | 2026-11-09 | |
| #17 | ChatGPT Image Latest (High Fidelity, 20251216)openai · Proprietary | 1,384.78 | 1,390.07 | 1.82 | 658,380 | overall | 2026-11-09 | |
| #18 | Gemini 3.1 Flash Image (nano-banana-2, Web Search)google · Proprietary | 1,383.56 | 1,389.75 | 2.49 | 268,912 | overall | 2026-11-09 | |
| #19 | Gemini 3 Pro Image Preview (nano-banana-pro)google · Proprietary | 1,382.03 | 1,387.76 | 2.14 | 533,223 | overall | 2026-11-09 | |
| #20 | Reve 2.1reve · Proprietary | 1,366.71 | 1,379 | 9.82 | 19,899 | overall | 2026-11-09 | |
| #21 | GPT-Image-1.5 (High Fidelity)openai · Proprietary | 1,364.75 | 1,369.92 | 1.74 | 683,303 | overall | 2026-11-09 | |
| #22 | Qwen-Image-2.1alibaba · qwen-research | 1,356.7 | 1,369 | 9.84 | 38,085 | overall | 2026-11-09 | |
| #23 | Reve 2.0reve · Proprietary | 1,352.63 | 1,365.67 | 11.06 | 18,628 | overall | 2026-11-09 | |
| #24 | Ideogram 4.5ideogram · Proprietary | 1,341.7 | 1,350.4 | 4.92 | 96,656 | overall | 2026-11-09 | |
| #25 | UNI-1.1 Maxluma-ai · Proprietary | 1,328.35 | 1,338.2 | 6.32 | 42,267 | overall | 2026-11-09 | |
| #26 | Grok Imagine Imagexai · Proprietary | 1,325.84 | 1,330.65 | 1.5 | 831,455 | overall | 2026-11-09 | |
| #27 | UNI-1.1luma-ai · Proprietary | 1,312.95 | 1,319.41 | 2.72 | 238,334 | overall | 2026-11-09 | |
| #28 | Gemini 3.1 Flash-Lite Image (nano-banana-2-lite)google · Proprietary | 1,307.93 | 1,317.53 | 5.99 | 63,235 | overall | 2026-11-09 | |
| #29 | Qwen-Image-2.0-Pro (2026-06-22)alibaba · Proprietary | 1,298 | 1,307.39 | 5.74 | 54,662 | overall | 2026-11-09 | |
| #30 | Seedream 4.5bytedance · Proprietary | 1,300.36 | 1,304.65 | 1.2 | 1,359,779 | overall | 2026-11-09 | |
| #31 | Wan 2.7 Image Proalibaba · Proprietary | 1,298.03 | 1,306.23 | 4.37 | 43,037 | overall | 2026-11-09 | |
| #32 | HunyuanImage 3.0 Instructtencent · tencent-hunyuan-community | 1,298.01 | 1,304.72 | 2.93 | 322,883 | overall | 2026-11-09 | |
| #33 | Wan 2.7 Imagealibaba · Proprietary | 1,296.5 | 1,304.28 | 3.94 | 43,850 | overall | 2026-11-09 | |
| #34 | Seedream 5.0 Litebytedance · Proprietary | 1,291 | 1,296.18 | 1.74 | 514,763 | overall | 2026-11-09 | |
| #35 | Gemini 2.5 Flash Image Preview (nano-banana)google · Proprietary | 1,289.45 | 1,293.53 | 1.08 | 11,423,284 | overall | 2026-11-09 | |
| #36 | Seedream 4.0 (2K)bytedance · Proprietary | 1,260.07 | 1,273.98 | 12.58 | 208,553 | overall | 2026-11-09 | |
| #37 | FLUX.2 [max]bfl · Proprietary | 1,258.55 | 1,264.86 | 2.6 | 367,896 | overall | 2026-11-09 | |
| #38 | Reve v1.1reve · Proprietary | 1,258.66 | 1,264.18 | 1.98 | 658,703 | overall | 2026-11-09 | |
| #39 | Kling Image O1kling · Proprietary | 1,246.64 | 1,254.04 | 3.57 | 140,278 | overall | 2026-11-09 | |
| #40 | FLUX.2 [pro]bfl · Proprietary | 1,244.94 | 1,250.07 | 1.71 | 670,980 | overall | 2026-11-09 | |
| #41 | Qwen-Image-Editalibaba · Apache 2.0 | 1,238.29 | 1,243.52 | 1.78 | 2,000,722 | overall | 2026-11-09 | |
| #42 | Reve v1reve · Proprietary | 1,229.73 | 1,239.69 | 6.45 | 391,118 | overall | 2026-11-09 | |
| #43 | Qwen-Image-Edit (2511)alibaba · Apache 2.0 | 1,230.3 | 1,235.87 | 2.02 | 472,602 | overall | 2026-11-09 | |
| #44 | Wan 2.6 Imagealibaba · Proprietary | 1,228.71 | 1,233.9 | 1.75 | 709,740 | overall | 2026-11-09 | |
| #45 | FLUX.2 [klein] 9Bbfl · flux-non-commercial-license | 1,221.56 | 1,227.34 | 2.17 | 529,025 | overall | 2026-11-09 | |
| #46 | FLUX.2 [flex]bfl · Proprietary | 1,221.25 | 1,227.55 | 2.59 | 434,160 | overall | 2026-11-09 | |
| #47 | FLUX.2 [dev]bfl · flux-non-commercial-license | 1,220.13 | 1,228.16 | 4.2 | 247,732 | overall | 2026-11-09 | |
| #48 | Seedream 4.0 (High Res, fal)bytedance · Proprietary | 1,212.89 | 1,218.5 | 2.05 | 1,212,501 | overall | 2026-11-09 | |
| #49 | P-Image-EditProprietary | 1,206.6 | 1,212.92 | 2.61 | 351,978 | overall | 2026-11-09 | |
| #50 | Seedream 4.0 (fal)bytedance · Proprietary | 1,203.26 | 1,215.56 | 9.84 | 151,431 | overall | 2026-11-09 | |
| #51 | Reve v1.1 Fastreve · Proprietary | 1,203.57 | 1,209.63 | 2.39 | 541,957 | overall | 2026-11-09 | |
| #52 | Reve Edit Fastreve · Proprietary | 1,193.84 | 1,202.15 | 4.49 | 227,505 | overall | 2026-11-09 | |
| #53 | FLUX.2 [klein] 4Bbfl · Apache 2.0 | 1,184.21 | 1,190.02 | 2.2 | 529,907 | overall | 2026-11-09 | |
| #54 | FLUX.1 Kontext [max]bfl · Proprietary | 1,179.28 | 1,184.9 | 2.06 | 390,740 | overall | 2026-11-09 | |
| #55 | Wan 2.5 Previewalibaba · Proprietary | 1,177.14 | 1,182.48 | 1.86 | 700,881 | overall | 2026-11-09 | |
| #56 | FLUX.1 Kontext [pro]bfl · Proprietary | 1,174.53 | 1,179.9 | 1.87 | 6,390,271 | overall | 2026-11-09 | |
| #57 | FLUX.1 Kontext [dev]bfl · flux-1-dev-non-commercial-license | 1,146.71 | 1,153.69 | 3.17 | 3,630,861 | overall | 2026-11-09 | |
| #58 | SeedEdit 3.0bytedance · Proprietary | 1,135.29 | 1,142.87 | 3.74 | 4,912,064 | overall | 2026-11-09 | |
| #59 | GPT-Image-1openai · Proprietary | 1,136.03 | 1,141.52 | 1.96 | 2,858,283 | overall | 2026-11-09 | |
| #60 | GPT-Image-1 miniopenai · Proprietary | 1,121.13 | 1,127.03 | 2.27 | 672,499 | overall | 2026-11-09 | |
| #61 | Gemini 2.0 Flash Preview Image Generationgoogle · Proprietary | 1,079.43 | 1,084.31 | 1.55 | 4,934,131 | overall | 2026-11-09 | |
| #62 | BAGELbytedance · Apache 2.0 | 1,020.85 | 1,032.36 | 8.63 | 13,472 | overall | 2026-11-09 | |
| #63 | Step1X-Editstepfun · Apache 2.0 | 991.62 | 1,000.75 | 5.42 | 155,350 | overall | 2026-11-09 |
用113个从零编写的长程真实软件工程任务测评编程Agent,同时刻画准确率(Pass@1)与真实花费/步数的性价比曲线,避免题目训练污染。
在新标签页打开独立跑分,不依赖厂商自报数据;综合 Intelligence Index 覆盖推理/编程/科学/知识,并联动速度、价格、上下文窗口等工程指标。
在新标签页打开每月更新全新题目防污染,全自动客观判分(唯一正确答案),聚焦数学/代码/推理/数据分析,学术圈公认权威。
在新标签页打开中文原创题库,深度贴合中文语境与政策文化,覆盖数学推理、代码、幻觉控制、智能体规划六大能力。
在新标签页打开上海AI实验室出品,20余家企业共建,五大能力维度、70+ 数据集,中英文模型均覆盖,并含真人投票的 Compass Arena。
在新标签页打开本页对战数据的官方原始来源,累计投票超过700万次,覆盖370+模型,逐票更新,界面本身也值得参考。
在新标签页打开