diff --git a/README.md b/README.md index feab8ad..f4abad9 100644 --- a/README.md +++ b/README.md @@ -45,16 +45,20 @@ The leaderboard is also hosted at: [physics-iq-verified.anates.ai](https://physi | 1 | [Magi-1 24B](https://arxiv.org/abs/2505.13211) + [GeoPhys (BoN)](https://christianinterno.github.io/GeoPhys/) (op) reported [here](https://christianinterno.github.io/GeoPhys/) | multiframe (v2v) | **58.2** ± 1.8
🥇 v2v | 2026-06-19 | | 2 | [Magi-1 24B](https://arxiv.org/abs/2505.13211) (op) reported [here](https://christianinterno.github.io/GeoPhys/) | multiframe (v2v) | **48.4** ± 1.1
🥈 v2v| 2026-06-19 | | 3 | [Cosmos3-Super-Image2Video](https://huggingface.co/nvidia/Cosmos3-Super-Image2Video) reported [here](https://github.com/google-deepmind/physics-IQ-benchmark/issues/75) | i2v | **42.7** ± 0.8
🥇 i2v | 2026-09-04 | -| 4 | [Cosmos3-Nano](https://huggingface.co/nvidia/Cosmos3-Nano) reported [here](https://github.com/google-deepmind/physics-IQ-benchmark/issues/75) | i2v | **37.3** ± 0.9
🥈 i2v | 2026-09-04 | -| 5 | [Grok Imagine Video](https://x.ai/news/grok-imagine-api) reported [here](https://arxiv.org/abs/2606.18943) | i2v | 34.8 ± 0.6
🥉 i2v | 2026-06-17 | -| 6 | [Magi-1 24B](https://arxiv.org/abs/2505.13211) + [GeoPhys (BoN)](https://christianinterno.github.io/GeoPhys/) (op) reported [here](https://christianinterno.github.io/GeoPhys/) | i2v | 33.7 ± 1.4 | 2026-06-19 | -| 7 | [Hunyuan Video 1.5](https://arxiv.org/abs/2511.18870) reported [here](https://arxiv.org/abs/2606.18943) | i2v | 33.4 ± 0.8 | 2026-06-17 | -| 8 | [Cosmos3-Edge](https://huggingface.co/nvidia/Cosmos3-Edge) reported [here](https://github.com/google-deepmind/physics-IQ-benchmark/issues/76) | i2v | 32.7 ± 1.1 | 2026-08-31 | -| 9 | [Wan 2.2](https://github.com/Wan-Video/Wan2.2) reported [here](https://arxiv.org/abs/2606.18943) | i2v | 32.2 ± 0.6 | 2026-06-17 | -| 10 | [Kandinsky-WM 1.0](https://huggingface.co/kandinskylab/Kandinsky-WM-1.0-I2V-5s-PH) reported [here](https://huggingface.co/datasets/Messimm/Kandinsky-WM-1.0-Physics-IQ-Verified) | i2v | 30.8 ± 0.9 | 2026-08-04 | -| 11 | [Magi-1 24B](https://arxiv.org/abs/2505.13211) (op) reported [here](https://christianinterno.github.io/GeoPhys/) | i2v | 30.2 ± 1.1 | 2026-06-19 | -| 12 | [Sora 2](https://openai.com/index/sora-2/) reported [here](https://arxiv.org/abs/2606.18943) | i2v | 26.5 ± 0.8 | 2026-06-17 | -| 13 | [P-Video](https://www.pruna.ai/p-video) reported [here](https://arxiv.org/abs/2606.18943) | i2v | 25.3 ± 1.8 | 2026-06-17 | +| 4 | [MiniMax H3](https://huggingface.co/MiniMaxAI/MiniMax-H3) (FL2VA) reported [here](https://github.com/google-deepmind/physics-IQ-benchmark/pull/80) | i2v | **39.8** ± 0.4
🥈 i2v | 2026-08-24 | +| 5 | [Cosmos3-Nano](https://huggingface.co/nvidia/Cosmos3-Nano) reported [here](https://github.com/google-deepmind/physics-IQ-benchmark/issues/75) | i2v | **37.3** ± 0.9
🥉 i2v | 2026-09-04 | +| 6 | [MiniMax H3 Max](https://fal.ai/models/minimax/h3-max/image-to-video) reported [here](https://github.com/google-deepmind/physics-IQ-benchmark/pull/80) | i2v | 36.2 ± 0.7 | 2026-08-27 | +| 7 | [Grok Imagine Video](https://x.ai/news/grok-imagine-api) reported [here](https://arxiv.org/abs/2606.18943) | i2v | 34.8 ± 0.6 | 2026-06-17 | +| 8 | [Magi-1 24B](https://arxiv.org/abs/2505.13211) + [GeoPhys (BoN)](https://christianinterno.github.io/GeoPhys/) (op) reported [here](https://christianinterno.github.io/GeoPhys/) | i2v | 33.7 ± 1.4 | 2026-06-19 | +| 9 | [Hunyuan Video 1.5](https://arxiv.org/abs/2511.18870) reported [here](https://arxiv.org/abs/2606.18943) | i2v | 33.4 ± 0.8 | 2026-06-17 | +| 10 | [Cosmos3-Edge](https://huggingface.co/nvidia/Cosmos3-Edge) reported [here](https://github.com/google-deepmind/physics-IQ-benchmark/issues/76) | i2v | 32.7 ± 1.1 | 2026-08-31 | +| 11 | [Wan 2.2 14B](https://github.com/Wan-Video/Wan2.2) reported [here](https://arxiv.org/abs/2606.18943) | i2v | 32.2 ± 0.6 | 2026-06-17 | +| 12 | [CogVideoX-5B](https://huggingface.co/zai-org/CogVideoX-5b-I2V) reported [here](https://github.com/google-deepmind/physics-IQ-benchmark/pull/80) | i2v | 31.8 ± 1.5 | 2026-08-18 | +| 13 | [Kandinsky-WM 1.0](https://huggingface.co/kandinskylab/Kandinsky-WM-1.0-I2V-5s-PH) reported [here](https://huggingface.co/datasets/Messimm/Kandinsky-WM-1.0-Physics-IQ-Verified) | i2v | 30.8 ± 0.9 | 2026-08-04 | +| 14 | [Magi-1 24B](https://arxiv.org/abs/2505.13211) (op) reported [here](https://christianinterno.github.io/GeoPhys/) | i2v | 30.2 ± 1.1 | 2026-06-19 | +| 15 | [Wan 2.2 5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B) reported [here](https://github.com/google-deepmind/physics-IQ-benchmark/pull/80) | i2v | 27.7 ± 0.9 | 2026-08-18 | +| 16 | [Sora 2](https://openai.com/index/sora-2/) reported [here](https://arxiv.org/abs/2606.18943) | i2v | 26.5 ± 0.8 | 2026-06-17 | +| 17 | [P-Video](https://www.pruna.ai/p-video) reported [here](https://arxiv.org/abs/2606.18943) | i2v | 25.3 ± 1.8 | 2026-06-17 | For details on the Physics-IQ Verified metrics, see the [arXiv report](https://arxiv.org/abs/2606.18943).