Model rankings
1260 models · 5 boards · 2 sources
Best images
Best open model
Best from China
Top three open models
Cosmos3-Super-Text2Image (agentic)NVIDIA · #5 overall1,241
HiDream-O1-Image-Dev-2604HiDream · #14 overall1,191
ERNIE ImageBaidu · #20 overall1,176
This week's changes
Fun-Realtime-TTSSpeech · #1New
claude-opus-4-8-thinkingCoding · #2New
Cosmos3-Super-Text2Image (agentic)Image · #5New
minimax-m3Coding · #6New
Krea 2 MediumImage · #7New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | New | Cosmos3-Super-Text2Image (agentic)OpenNVIDIA | 1,241 | ±11 |
| 2 | ▼ 1 | HiDream-O1-Image-Dev-2604OpenHiDream · 1 more variant | 1,191 | ±9 |
| 3 | New | ERNIE ImageOpenBaidu | 1,176 | ±11 |
| 4 | New | ERNIE Image TurboOpenBaidu | 1,167 | ±10 |
| 5 | ▼ 3 | Qwen Image Max 2512OpenAlibaba | 1,161 | ±9 |
| 6 | ▼ 3 | FLUX.2 [dev]OpenBlack Forest Labs | 1,159 | ±9 |
| 7 | ▼ 3 | FLUX.2 [dev] TurboOpenFal | 1,156 | ±9 |
| 8 | ▼ 3 | FLUX.2 [dev] FlashOpenFal | 1,141 | ±9 |
| 9 | ▼ 3 | FLUX.2 [klein] 9BOpenBlack Forest Labs | 1,124 | ±9 |
| 10 | ▼ 3 | HunyuanImage 3.0 (Fal)OpenTencent | 1,124 | ±9 |
| 11 | ▼ 3 | HiDream-O1-ImageOpenHiDream | 1,121 | ±10 |
| 12 | ▼ 3 | HunyuanImage 3.0 Instruct (Fal)OpenTencent | 1,112 | ±9 |
| 13 | ▼ 3 | Z-Image TurboOpenAlibaba | 1,105 | ±8 |
| 14 | ▼ 3 | FLUX.2 [klein] Base 9BOpenBlack Forest Labs | 1,084 | ±9 |
| 15 | ▼ 2 | SRPOOpenTencent | 1,074 | ±9 |
| 16 | ▼ 4 | FIBOOpenBria | 1,073 | ±9 |
| 17 | ▼ 2 | HunyuanImage 2.1OpenTencent | 1,068 | ±8 |
| 18 | ▼ 4 | FLUX.2 [klein] 4BOpenBlack Forest Labs | 1,067 | ±9 |
| 19 | ▼ 1 | HiDream-I1-FastOpenHiDream | 1,061 | ±9 |
| 20 | ▼ 4 | Qwen ImageOpenAlibaba | 1,060 | ±9 |
| 21 | ▼ 4 | HiDream-I1-DevOpenHiDream | 1,060 | ±9 |
| 22 | ▼ 3 | GLM-ImageOpenZ AI | 1,050 | ±9 |
| 23 | ▼ 3 | Infinity 8BOpenByteDance | 1,046 | ±9 |
| 24 | ▼ 3 | LongCat ImageOpenMeituan | 1,035 | ±9 |
| 25 | ▼ 3 | FLUX.1 Krea [dev]OpenBlack Forest Labs | 1,035 | ±12 |
| 26 | ▼ 3 | FLUX.1 [dev]OpenBlack Forest Labs | 1,030 | ±8 |
| 27 | ▼ 3 | Stable Diffusion 3.5 LargeOpenStability.ai | 1,028 | ±8 |
| 28 | ▼ 3 | Stable Diffusion 3.5 Large TurboOpenStability.ai | 1,019 | ±8 |
| 29 | ▼ 3 | FLUX.1 [schnell]OpenBlack Forest Labs | 1,000 | ±0 |
| 30 | ▼ 3 | FLUX.2 [klein] Base 4BOpenBlack Forest Labs | 974 | ±9 |
| 31 | ▼ 3 | Lumina Image v2OpenOpenGVLab | 969 | ±9 |
| 32 | ▼ 3 | Playground v2.5OpenPlayground AI | 967 | ±8 |
| 33 | ▼ 3 | Stable Diffusion 3.5 MediumOpenStability.ai | 942 | ±10 |
| 34 | ▼ 3 | Sana Sprint 1.6BOpenNVIDIA | 936 | ±10 |
| 35 | ▼ 3 | Stable Diffusion 3 MediumOpenStability.ai | 913 | ±9 |
| 36 | ▼ 3 | SDXL LightningOpenByteDance | 907 | ±9 |
| 37 | ▼ 3 | OmniGen V2OpenVectorSpaceLab | 907 | ±10 |
| 38 | ▼ 3 | BagelOpenByteDance | 905 | ±10 |
| 39 | ▼ 3 | Bria 3.2OpenBria | 901 | ±10 |
| 40 | ▼ 3 | Stable Diffusion XL 1.0OpenStability.ai | 873 | ±9 |
| 41 | ▼ 3 | Stable Diffusion 2.1OpenStability.ai | 750 | ±11 |
| 42 | ▼ 3 | Janus ProOpenDeepSeek | 715 | ±13 |
| 43 | ▼ 3 | Stable Diffusion 1.5OpenStability.ai | 658 | ±13 |
Intelligence over time
Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi