Model rankings
1539 models · 5 boards · 2 sources
Best video
Best open model
Best from China
Top three open models
MiniMax H3MiniMax · #3 overall1,302
LTX-2.5 FastLightricks · #16 overall1,217
LTX-2.5 ProLightricks · #22 overall1,209
This week's changes
Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)Intelligence · #1New
Eleven v4Speech · #1New
Qwen-Audio-3.1-TTS-PlusSpeech · #2New
claude-sonnet-5.5-xhighCoding · #3New
gpt-6.1-sol-maxCoding · #4New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | MiniMax H3OpenMiniMax | 1,302 | ±11 |
| 2 | — | LTX-2.5 FastOpenLightricks | 1,217 | ±11 |
| 3 | — | LTX-2.5 ProOpenLightricks | 1,209 | ±11 |
| 4 | — | LTX-2 ProOpenLightricks | 1,127 | ±8 |
| 5 | — | LTX-2 FastOpenLightricks | 1,125 | ±8 |
| 6 | — | LTX-2.3 ProOpenLightricks | 1,125 | ±9 |
| 7 | — | LTX-2.3 FastOpenLightricks | 1,121 | ±9 |
| 8 | — | Wan 2.2 A14BOpenAlibaba | 1,116 | ±8 |
| 9 | — | HunyuanVideo-1.5 (Fal)OpenTencent | 1,020 | ±9 |
| 10 | — | Wan 2.1 14BOpenAlibaba | 1,018 | ±9 |
| 11 | — | Mochi 1OpenGenmo | 1,000 | ±0 |
| 12 | — | Hunyuan Video (Fal)OpenTencent | 992 | ±9 |
| 13 | — | Krea RealtimeOpenKrea | 982 | ±10 |
| 14 | — | Wan 2.2 5BOpenAlibaba | 950 | ±10 |
| 15 | — | CogVideoX-5BOpenZ AI | 805 | ±10 |
| 16 | — | Pyramid FlowOpenOpen Source | 778 | ±11 |
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