Skip to content

Add recent Physics-IQ Verified leaderboard entries #80

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
rgeirhos merged 2 commits into from
Sep 4, 2026
Merged

Add recent Physics-IQ Verified leaderboard entries #80

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
008659f
Add verified leaderboard entries
tuliti Sep 4, 2026
2d24ccb
Clarify Wan 2.2 14B leaderboard entry
tuliti Sep 4, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 14 additions & 10 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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/) <small>(op)</small> reported [here](https://christianinterno.github.io/GeoPhys/) | multiframe (v2v) | **58.2** <small>± 1.8</small> <br> 🥇 v2v | 2026-06-19 |
| 2 | [Magi-1 24B](https://arxiv.org/abs/2505.13211) <small>(op)</small> reported [here](https://christianinterno.github.io/GeoPhys/) | multiframe (v2v) | **48.4** <small>± 1.1</small> <br> 🥈 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** <small>± 0.8</small> <br> 🥇 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** <small>± 0.9</small> <br> 🥈 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 <small>± 0.6</small> <br> 🥉 i2v | 2026-06-17 |
| 6 | [Magi-1 24B](https://arxiv.org/abs/2505.13211) + [GeoPhys (BoN)](https://christianinterno.github.io/GeoPhys/) <small>(op)</small> reported [here](https://christianinterno.github.io/GeoPhys/) | i2v | 33.7 <small>± 1.4</small> | 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 <small>± 0.8</small> | 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 <small>± 1.1</small> | 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 <small>± 0.6</small> | 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 <small>± 0.9</small> | 2026-08-04 |
| 11 | [Magi-1 24B](https://arxiv.org/abs/2505.13211) <small>(op)</small> reported [here](https://christianinterno.github.io/GeoPhys/) | i2v | 30.2 <small>± 1.1</small> | 2026-06-19 |
| 12 | [Sora 2](https://openai.com/index/sora-2/) reported [here](https://arxiv.org/abs/2606.18943) | i2v | 26.5 <small>± 0.8</small> | 2026-06-17 |
| 13 | [P-Video](https://www.pruna.ai/p-video) reported [here](https://arxiv.org/abs/2606.18943) | i2v | 25.3 <small>± 1.8</small> | 2026-06-17 |
| 4 | [MiniMax H3](https://huggingface.co/MiniMaxAI/MiniMax-H3) <small>(FL2VA)</small> reported [here](https://github.com/google-deepmind/physics-IQ-benchmark/pull/80) | i2v | **39.8** <small>± 0.4</small> <br> 🥈 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** <small>± 0.9</small> <br> 🥉 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 <small>± 0.7</small> | 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 <small>± 0.6</small> | 2026-06-17 |
| 8 | [Magi-1 24B](https://arxiv.org/abs/2505.13211) + [GeoPhys (BoN)](https://christianinterno.github.io/GeoPhys/) <small>(op)</small> reported [here](https://christianinterno.github.io/GeoPhys/) | i2v | 33.7 <small>± 1.4</small> | 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 <small>± 0.8</small> | 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 <small>± 1.1</small> | 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 <small>± 0.6</small> | 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 <small>± 1.5</small> | 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 <small>± 0.9</small> | 2026-08-04 |
| 14 | [Magi-1 24B](https://arxiv.org/abs/2505.13211) <small>(op)</small> reported [here](https://christianinterno.github.io/GeoPhys/) | i2v | 30.2 <small>± 1.1</small> | 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 <small>± 0.9</small> | 2026-08-18 |
| 16 | [Sora 2](https://openai.com/index/sora-2/) reported [here](https://arxiv.org/abs/2606.18943) | i2v | 26.5 <small>± 0.8</small> | 2026-06-17 |
| 17 | [P-Video](https://www.pruna.ai/p-video) reported [here](https://arxiv.org/abs/2606.18943) | i2v | 25.3 <small>± 1.8</small> | 2026-06-17 |

For details on the Physics-IQ Verified metrics, see the [arXiv report](https://arxiv.org/abs/2606.18943).

Expand Down