LOADINGLoading
84 models
| Rank | Model | Rating | Rating lower bound | Rating upper bound | Variance | Votes | Category | Source updated |
|---|---|---|---|---|---|---|---|---|
| #1 | GPT-Image-2.5 Sunburstopenai · Proprietary | 1,423.53 | 1,434.07 | 7.22 | 57,928 | overall | 2026-11-09 | |
| #2 | GPT-Image-2.6 Sunburst (Medium)openai · Proprietary | 1,392.76 | 1,419.47 | 46.44 | 2,718 | overall | 2026-11-09 | |
| #3 | GPT-Image-2.5 Flareopenai · Proprietary | 1,395.09 | 1,405.33 | 6.83 | 57,020 | overall | 2026-11-09 | |
| #4 | GPT-Image-2.6 Flare (Medium)openai · Proprietary | 1,369.69 | 1,395.97 | 44.96 | 2,551 | overall | 2026-11-09 | |
| #5 | GPT-Image-2 (Medium)openai · Proprietary | 1,377.84 | 1,385.63 | 3.95 | 106,021 | overall | 2026-11-09 | |
| #6 | MAI-Image-2.6microsoft-ai · Proprietary | 1,324.15 | 1,334.54 | 7.03 | 38,700 | overall | 2026-11-09 | |
| #7 | Gemini Nano Banana 2.1google · Proprietary | 1,318.58 | 1,336.79 | 21.59 | 4,966 | overall | 2026-11-09 | |
| #8 | Grok Imagine Image 2.0xai · Proprietary | 1,311.17 | 1,326.09 | 14.49 | 9,959 | overall | 2026-11-09 | |
| #9 | Reve 2.1reve · Proprietary | 1,294.21 | 1,309.47 | 15.16 | 7,909 | overall | 2026-11-09 | |
| #10 | Grok Imagine Image 2.0 (20260801)xai · Proprietary | 1,282.62 | 1,293.28 | 7.4 | 32,600 | overall | 2026-11-09 | |
| #11 | Reve 2.0reve · Proprietary | 1,261.94 | 1,274.42 | 10.14 | 15,323 | overall | 2026-11-09 | |
| #12 | Muse Imagemeta · Proprietary | 1,261.89 | 1,270.97 | 5.37 | 57,330 | overall | 2026-11-09 | |
| #13 | Gemini 3.1 Flash Image (nano-banana-2, Web Search)google · Proprietary | 1,252.62 | 1,260.37 | 3.92 | 77,579 | overall | 2026-11-09 | |
| #14 | Qwen-Image-3.0-Proalibaba · Proprietary | 1,247.6 | 1,260.82 | 11.38 | 10,915 | overall | 2026-11-09 | |
| #15 | MAI-Image-2.5microsoft-ai · Proprietary | 1,248.33 | 1,256.8 | 4.67 | 59,127 | overall | 2026-11-09 | |
| #16 | Gemini 3.1 Flash-Lite Image (nano-banana-2-lite)google · Proprietary | 1,243.15 | 1,255.3 | 9.6 | 17,149 | overall | 2026-11-09 | |
| #17 | Seedream 5.0 Probytedance · Proprietary | 1,245.05 | 1,252.7 | 3.81 | 107,413 | overall | 2026-11-09 | |
| #18 | Gemini 3 Pro Image (nano-banana-pro, 2K)google · Proprietary | 1,242.73 | 1,248.77 | 2.37 | 185,022 | overall | 2026-11-09 | |
| #19 | GPT-Image-1.5 (High Fidelity)openai · Proprietary | 1,232.93 | 1,239.07 | 2.45 | 169,495 | overall | 2026-11-09 | |
| #20 | Gemini 3 Pro Image Preview (nano-banana-pro)google · Proprietary | 1,226.3 | 1,236.15 | 6.32 | 83,834 | overall | 2026-11-09 | |
| #21 | Qwen-Image-2.1alibaba · qwen-research | 1,220.45 | 1,233.06 | 10.35 | 17,883 | overall | 2026-11-09 | |
| #22 | Ideogram 4.0 (Quality)ideogram · Ideogram Open Model | 1,195.52 | 1,203.03 | 3.67 | 77,406 | overall | 2026-11-09 | |
| #23 | Qwen-Image-2.0-Pro (2026-06-22)alibaba · Proprietary | 1,184.23 | 1,196.09 | 9.16 | 12,670 | overall | 2026-11-09 | |
| #24 | UNI-1.1 Maxluma-ai · Proprietary | 1,182.18 | 1,194.59 | 10.03 | 13,748 | overall | 2026-11-09 | |
| #25 | MAI-Image-2microsoft-ai · Proprietary | 1,178.17 | 1,187.33 | 5.46 | 50,455 | overall | 2026-11-09 | |
| #26 | UNI-1.1luma-ai · Proprietary | 1,177.45 | 1,185.77 | 4.5 | 58,725 | overall | 2026-11-09 | |
| #27 | Recraft V4.1 Utility Prorecraft · Proprietary | 1,158.16 | 1,180.41 | 32.2 | 2,565 | overall | 2026-11-09 | |
| #28 | Grok Imagine Imagexai · Proprietary | 1,165.77 | 1,171.06 | 1.82 | 287,761 | overall | 2026-11-09 | |
| #29 | Cosmos3-Super-Text2Image (Agentic)nvidia · OpenMDW-1.1 | 1,157.08 | 1,171.43 | 13.41 | 10,160 | overall | 2026-11-09 | |
| #30 | FLUX.2 [max]bfl · Proprietary | 1,157.58 | 1,164.67 | 3.27 | 120,498 | overall | 2026-11-09 | |
| #31 | Grok Imagine Image Proxai · Proprietary | 1,156.16 | 1,163.77 | 3.77 | 97,014 | overall | 2026-11-09 | |
| #32 | FLUX.2 [flex]bfl · Proprietary | 1,152.92 | 1,159.75 | 3.04 | 153,015 | overall | 2026-11-09 | |
| #33 | Reve v1.5reve · Proprietary | 1,149.87 | 1,158.43 | 4.78 | 38,512 | overall | 2026-11-09 | |
| #34 | FLUX.2 [pro]bfl · Proprietary | 1,149.85 | 1,155.56 | 2.12 | 219,196 | overall | 2026-11-09 | |
| #35 | HunyuanImage 3.0tencent · tencent-hunyuan-community | 1,148.22 | 1,154.92 | 2.92 | 175,293 | overall | 2026-11-09 | |
| #36 | Cosmos3-Super-Text2Imagenvidia · OpenMDW-1.1 | 1,143.71 | 1,155.71 | 9.36 | 17,450 | overall | 2026-11-09 | |
| #37 | Gemini 2.5 Flash Image Preview (nano-banana)google · Proprietary | 1,146.1 | 1,150.92 | 1.51 | 894,571 | overall | 2026-11-09 | |
| #38 | Seedream 4.5bytedance · Proprietary | 1,145.28 | 1,150.44 | 1.73 | 312,425 | overall | 2026-11-09 | |
| #39 | Imagen 4 Ultra (generate-001)google · Proprietary | 1,141.52 | 1,150.17 | 4.88 | 385,852 | overall | 2026-11-09 | |
| #40 | FLUX.2 [dev]bfl · flux-non-commercial-license | 1,140.93 | 1,149.29 | 4.55 | 75,695 | overall | 2026-11-09 | |
| #41 | Seedream 5.0 Litebytedance · Proprietary | 1,137.42 | 1,143.69 | 2.55 | 143,894 | overall | 2026-11-09 | |
| #42 | Wan 2.6alibaba · Proprietary | 1,135.73 | 1,141.24 | 1.98 | 248,684 | overall | 2026-11-09 | |
| #43 | Seedream 4.0 (2K)bytedance · Proprietary | 1,131.68 | 1,144.85 | 11.29 | 12,274 | overall | 2026-11-09 | |
| #44 | Recraft V4.1 Prorecraft · Proprietary | 1,121.03 | 1,142.19 | 29.13 | 2,745 | overall | 2026-11-09 | |
| #45 | Krea 2 Mediumkrea · Proprietary | 1,124.2 | 1,132.08 | 4.03 | 74,643 | overall | 2026-11-09 | |
| #46 | Imagen 4 (generate-001)google · Proprietary | 1,124.96 | 1,130.48 | 1.98 | 533,366 | overall | 2026-11-09 | |
| #47 | Qwen-Image (2512)alibaba · Apache 2.0 | 1,120.45 | 1,127.43 | 3.17 | 95,381 | overall | 2026-11-09 | |
| #48 | Wan 2.5 Previewalibaba · Proprietary | 1,114.59 | 1,120.16 | 2.02 | 284,183 | overall | 2026-11-09 | |
| #49 | Recraft V4recraft · Proprietary | 1,112.77 | 1,118.99 | 2.52 | 152,609 | overall | 2026-11-09 | |
| #50 | Seedream 4.0 (fal)bytedance · Proprietary | 1,109.26 | 1,122.36 | 11.16 | 11,708 | overall | 2026-11-09 | |
| #51 | Krea 2 Turbokrea · krea-2-community-license | 1,111.31 | 1,119.97 | 4.88 | 63,653 | overall | 2026-11-09 | |
| #52 | GPT-Image-1openai · Proprietary | 1,111.69 | 1,118.06 | 2.65 | 265,925 | overall | 2026-11-09 | |
| #53 | HiDream-O1-Imagehidream · MIT | 1,110.94 | 1,118.33 | 3.55 | 75,930 | overall | 2026-11-09 | |
| #54 | Krea 2 Largekrea · Proprietary | 1,109.9 | 1,118.05 | 4.32 | 68,026 | overall | 2026-11-09 | |
| #55 | Seedream 4.0 (High Res, fal)bytedance · Proprietary | 1,109.39 | 1,115.93 | 2.78 | 178,506 | overall | 2026-11-09 | |
| #56 | GPT-Image-1 miniopenai · Proprietary | 1,105.82 | 1,112.26 | 2.7 | 167,858 | overall | 2026-11-09 | |
| #57 | Wan 2.7 Image Proalibaba · Proprietary | 1,098.21 | 1,108.35 | 6.69 | 29,817 | overall | 2026-11-09 | |
| #58 | Wan 2.7 Imagealibaba · Proprietary | 1,094.83 | 1,104.88 | 6.57 | 30,252 | overall | 2026-11-09 | |
| #59 | Recraft V4.1 Flashrecraft · Proprietary | 1,087.98 | 1,107.83 | 25.63 | 3,220 | overall | 2026-11-09 | |
| #60 | MAI-Image-1microsoft-ai · Proprietary | 1,089.02 | 1,096.31 | 3.46 | 96,286 | overall | 2026-11-09 | |
| #61 | Z-Image-Turboalibaba · Apache 2.0 | 1,076.47 | 1,087.24 | 7.55 | 24,125 | overall | 2026-11-09 | |
| #62 | Seedream 3.0bytedance · Proprietary | 1,076.14 | 1,086.31 | 6.73 | 36,197 | overall | 2026-11-09 | |
| #63 | FLUX.1 Kontext [max]bfl · Proprietary | 1,071.84 | 1,078.35 | 2.76 | 65,276 | overall | 2026-11-09 | |
| #64 | FLUX.2 [klein] 9Bbfl · flux-non-commercial-license | 1,066.76 | 1,073.26 | 2.75 | 147,202 | overall | 2026-11-09 | |
| #65 | Qwen-Image (Prompt Extend)alibaba · Apache 2.0 | 1,058.75 | 1,064.18 | 1.92 | 706,651 | overall | 2026-11-09 | |
| #66 | FLUX.1 Kontext [pro]bfl · Proprietary | 1,055.46 | 1,062.37 | 3.1 | 329,922 | overall | 2026-11-09 | |
| #67 | Qwen-Imagealibaba · Apache 2.0 | 1,054.35 | 1,059.63 | 1.82 | 84,293 | overall | 2026-11-09 | |
| #68 | Imagen 3 (generate-002)google · Proprietary | 1,053.63 | 1,060.16 | 2.78 | 358,317 | overall | 2026-11-09 | |
| #69 | Ideogram 3.0 (Quality)ideogram · Proprietary | 1,045.15 | 1,052.73 | 3.73 | 115,848 | overall | 2026-11-09 | |
| #70 | Luma Photonluma-ai · Proprietary | 1,031.92 | 1,039.41 | 3.66 | 127,882 | overall | 2026-11-09 | |
| #71 | P-ImageProprietary | 1,029.14 | 1,036.15 | 3.2 | 107,203 | overall | 2026-11-09 | |
| #72 | FLUX.2 [klein] 4Bbfl · Apache 2.0 | 1,026.69 | 1,033.22 | 2.77 | 148,810 | overall | 2026-11-09 | |
| #73 | Runway Gen-4runway · Proprietary | 1,019.67 | 1,028.63 | 5.23 | 53,242 | overall | 2026-11-09 | |
| #74 | Recraft V3recraft · Proprietary | 1,018.33 | 1,025.74 | 3.57 | 193,008 | overall | 2026-11-09 | |
| #75 | FLUX1.1 [pro]bfl · Proprietary | 1,012.16 | 1,019.15 | 3.18 | 70,460 | overall | 2026-11-09 | |
| #76 | Ideogram 2.0ideogram · Proprietary | 1,009.81 | 1,016.92 | 3.29 | 72,090 | overall | 2026-11-09 | |
| #77 | Lucid Originleonardo-ai · Proprietary | 1,009.52 | 1,016.36 | 3.05 | 284,819 | overall | 2026-11-09 | |
| #78 | GLM-Imagezai · MIT | 1,003.13 | 1,020.97 | 20.72 | 4,761 | overall | 2026-11-09 | |
| #79 | Gemini 2.0 Flash Preview Image Generationgoogle · Proprietary | 972.59 | 979.55 | 3.15 | 255,481 | overall | 2026-11-09 | |
| #80 | FLUX.1 [dev] (FP8)bfl · Open | 965.69 | 973.16 | 3.63 | 49,221 | overall | 2026-11-09 | |
| #81 | DALL-E 3openai · Proprietary | 963.93 | 971.42 | 3.65 | 238,180 | overall | 2026-11-09 | |
| #82 | FLUX.1 Kontext [dev]bfl · flux-1-dev-non-commercial-license | 937.68 | 945.27 | 3.75 | 214,391 | overall | 2026-11-09 | |
| #83 | Stable Diffusion 3.5 LargeOpen | 933.83 | 942.8 | 5.23 | 23,396 | overall | 2026-11-09 | |
| #84 | BAGELbytedance · Apache 2.0 | 891.44 | 903.02 | 8.72 | 12,316 | 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.
