Benchmarks
How open-weight models stack up — across reasoning, code, vision, and image generation. Cached from public sources and refreshed every 12 hours.
Artificial Analysis Intelligence Index — a blended measure of reasoning, knowledge, and coding across open-weight and proprietary language models.
Best value · intelligence vs. price
How much capability each open model delivers per dollar. Models on the frontier (top-left) lead on value.
Every board
Artificial Analysis Intelligence Index — a blended measure of reasoning, knowledge, and coding across open-weight and proprietary language models.
| # | Model | Intelligence |
|---|---|---|
| 1 | DeepSeek V4.1 Flash 1017 DeepSeek | 32.5 |
| 2 | GLM-5.3 Zhipu AI | 31.7 |
| 3 | GLM-5.3-Flash Zhipu AI | 27.8 |
| 4 | DeepSeek V4 Pro 0813 DeepSeek | 23.1 |
| 5 | Qwen3.8 27B Qwen · Alibaba | 20.1 |
Human-preference Elo for text-to-image models from the Artificial Analysis Arena — open-weight and proprietary, ranked head-to-head.
| # | Model | Elo |
|---|---|---|
| 1 | FLUX 3 Image Black Forest Labs | 1,117 |
| 2 | FLUX 3 Image Klein Black Forest Labs | 1,043 |
| 3 | Qwen-Image-2.1 Qwen · Alibaba | 1,042 |
| 4 | FLUX.2 [dev] Black Forest Labs | 1,000 |
| 5 | FLUX.2 [dev] Turbo Fal | 994 |
Human-preference Elo for instruction-based image editing models, ranked head-to-head in the Artificial Analysis Arena.
| # | Model | Elo |
|---|---|---|
| 1 | FLUX 3 Image Black Forest Labs | 1,122 |
| 2 | Qwen-Image-2.1 Qwen · Alibaba | 1,081 |
| 3 | FLUX 3 Image Klein Black Forest Labs | 1,072 |
| 4 | HunyuanImage 3.0 Instruct Tencent | 1,063 |
| 5 | HunyuanImage 3.0 Tencent | 1,029 |
Human-preference Elo for text-to-video models from the Artificial Analysis Arena — the fastest-moving open-vs-proprietary race in generative AI.
| # | Model | Elo |
|---|---|---|
| 1 | FLUX 3 Black Forest Labs | 1,092 |
| 2 | LTX-2.5 Fast Lightricks | 929 |
| 3 | LTX-2.3 Fast Lightricks | 845 |
Human-preference Elo for image-to-video models, ranked head-to-head in the Artificial Analysis Arena.
| # | Model | Elo |
|---|---|---|
| 1 | FLUX 3 Black Forest Labs | 1,040 |
| 2 | LTX-2.5 Fast Lightricks | 920 |
| 3 | LTX-2.3 Fast Lightricks | 823 |
Human-preference Elo for text-to-speech models from the Artificial Analysis Arena — open-weight and proprietary voices, ranked head-to-head.
| # | Model | Elo |
|---|---|---|
| 1 | Falcon 2 Murf AI | 1,156 |
| 2 | Maya 2 Flash Maya Research | 1,062 |
| 3 | Kokoro 82M v1.0 Kokoro | 1,062 |
| 4 | Maya1 Maya Research | 1,046 |
| 5 | Higgs Audio V3 TTS Boson AI | 1,039 |
Aggregate of contamination-resistant benchmarks — IFEval, BBH, MATH, GPQA, MUSR, MMLU-Pro — for open-weight language models. The final snapshot of Hugging Face's Open LLM Leaderboard.
| # | Model | Avg. |
|---|---|---|
| 1 | MaziyarPanahi/calme-3.2-instruct-78b | 52.1 |
| 2 | MaziyarPanahi/calme-3.1-instruct-78b | 51.3 |
| 3 | dfurman/CalmeRys-78B-Orpo-v0.1 | 51.2 |
| 4 | MaziyarPanahi/calme-2.4-rys-78b | 50.8 |
| 5 | huihui-ai/Qwen2.5-72B-Instruct-abliterated | 48.1 |
The most-downloaded open-weight models on Hugging Face over the last 30 days — the community's working set, straight from the Hub and refreshed every 12 hours.
The most-liked open-weight models on Hugging Face — a durable signal of community esteem spanning every modality, refreshed every 12 hours.
| # | Model | Likes |
|---|---|---|
| 1 | Qwen/Qwen3.8-27B Qwen · Alibaba | 18.9K |
| 2 | Black Forest Labs | 15.9K |
| 3 | deepseek-ai/DeepSeek-R1 DeepSeek | 14.4K |
| 4 | Moonshot AI | 11.9K |
| 5 | Lightricks/LTX-2.5 | 10.1K |