AI model leaderboards
Frontier and open-weight model rankings, what developers actually run, and the most-downloaded open video models. Each board links to its source.
Frontier models
Blind head-to-head votes from real users, aggregated into an Elo rating. Higher means the model won more pairwise comparisons.
| # | Model | Org | Elo |
|---|---|---|---|
| 1 | Claude Fable 5 | Anthropic | 1507 |
| 2 | Claude Opus 4.6-high | Anthropic | 1505 |
| 3 | Muse Spark 1.2 | Meta | 1498 |
| 4 | Gemini 3.1 Pro | 1487 | |
| 5 | GPT-5.6 Sol | OpenAI | 1481 |
| 6 | Qwen3.8-Max | Alibaba | 1479 |
| 7 | Grok 4.6 | xAI | 1461 |
Elo is relative — a 20-point gap is small; only large gaps are meaningful.
Open-weight models
Open-weight models you can download and self-host, scored on a 0–100 composite index.
| # | Model | Org | index |
|---|---|---|---|
| 1 | Qwen3.8-Max | Alibaba | 79 |
| 2 | Kimi K3 | Moonshot | 60 |
| 3 | GLM-5.3 | Z.ai | 58 |
| 4 | DeepSeek V4 | DeepSeek | 58 |
| 5 | Llama 4 | Meta | 52 |
Scored 0–100. Not comparable with the Elo ratings on the frontier board.
Source: Open-weights rankings ↗
Most used on OpenRouter
What developers actually run: models ranked by tokens processed through OpenRouter over the last day.
| # | Model | Org | T tokens |
|---|---|---|---|
| 1 | deepseek-v4-flash | deepseek | 12.19 |
| 2 | ox-alpha | stealth | 9.75 |
| 3 | gpt-5.6-luna | openai | 8.48 |
| 4 | glm-5.3-flash | z-ai | 8.14 |
| 5 | mimo-v2.5 | xiaomi | 8.08 |
| 6 | hy3 | tencent | 6.41 |
| 7 | nemotron-3-ultra-550b-a55b | nvidia | 4.93 |
| 8 | hy4-preview | tencent | 4.01 |
| 9 | gemini-3.7-flash | 3.85 | |
| 10 | minimax-m3 | minimax | 3.02 |
Trillions of tokens processed. Usage, not quality — cheap and free models rank high here.
Open-weight video models
Open-weight video generators you can download and run, ranked by downloads across every variant of each model.
| # | Model | Org | M downloads |
|---|---|---|---|
| 1 | Wan2.2 | Wan-AI | 6.48 |
| 2 | MiniMax-H3 | larryvrh | 4.02 |
| 3 | LTX-2.3 | Lightricks | 2.57 |
| 4 | Wan2.1 | Wan-AI | 2.07 |
| 5 | LTX-2.5 | Lightricks | 1.49 |
| 6 | LTX-Video | Lightricks | 0.5 |
| 7 | LTX-2 | Lightricks | 0.38 |
| 8 | Sulphur-2 | SulphurAI | 0.35 |
| 9 | stable-video-diffusion-img2vid | stabilityai | 0.25 |
| 10 | Cosmos-Predict2 | nvidia | 0.18 |
Millions of downloads, summing quantised and repackaged variants into their base model.