MVPBench
gemini-robotics-er-1.5-preview 72.5% leads since September 2025 Models answer video questions on spatial, temporal and intuitive physics. Each question comes in a pair of near-identical videos with opposite answers, so text or single-frame shortcuts fail.
Released with V-JEPA 2. The leaderboard uses the mini split of about 5,700 items. Videos come from nine public datasets.
- Made by
- Meta FAIR
- Released
- June 2025
- Kind
- Physical prediction
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Last in a launch post
- June 2025, dropped before it saturated
- Last model added
- May 2026
gemini-robotics-er-1.5-preview leads with 72.5% among models released by July 2026
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in July 2026, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
- Gemini 4 Carbon
- GPT-6 Astra
- Claude Opus 5.5
- and 16 more
- 1 gemini-robotics-er-1.5-preview 72.5%
- 2
Cosmos3-Nano 66.9% - 3 Cosmos3-Edge 53.3%
- 4
V-JEPA 2 44.5%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | gemini-robotics-er-1.5-preview | 72.5% | Sep 2025 | Lab model card | |
| 2 | Cosmos3-Nano | 66.9% | May 2026 | Lab model card | |
| 3 | Cosmos3-Edge | 53.3% | May 2026 | Lab model card | |
| 4 | V-JEPA 2 | 44.5% | Jun 2025 | Lab model card |
2 models have held number one in labs’ own numbers since its release in June 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Labs’ model cards
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Labs’ model cards
No launch post has listed it since June 2025
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Jun 11, 2025 | V-JEPA 2 | 44.5 | MVP (Video QA) |
3 system cards report it, from 2 labs
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| May 31, 2026 | Cosmos3-Nano technical report | 66.9 | MVPBench, Cosmos3-Nano 8B column, Table 10 | Capabilities |
| May 31, 2026 | Cosmos3-Edge technical report | 53.3 | MVPBench, Cosmos3-Edge 2B column, Table 10 | Capabilities |
| Sep 25, 2025 | gemini-robotics-er-1.5-preview technical report | 72.5 | Min Video Pairs (Table 19, thinking on). Thinking off 67.1 | Capabilities |
More in World models
- AgentWorldBench In use Language world models predict the next environment observation after an agent action, in 7 domains from MCP and search to Android and desktop OS. A judge model scores each prediction against the real observation on five dimensions. GPT-5.4 58.3
- IntPhys 2 In use Models watch simulated videos and judge whether each event is physically possible, testing object permanence, immutability, continuity and solidity. Scored by accuracy. Muse Spark Open 68.3%
- QwenWorldBench Fading Models act as world models that simulate agent environments in 7 domains, such as terminal, web, and Android. A rubric judge scores five dimensions.
Qwen3.7-Plus 62.1% - VPCT Fading Models view an image of a ball, ramps, and three buckets and predict which bucket the ball falls into. Scored by accuracy on 100 problems. Gemini 3 Pro 91%
- ContPhy Fading Models infer physical properties such as mass and density of fluids and soft bodies from videos and predict their dynamics.
Seed2.0 Pro 67.4% - RBench Only in system cards 650 image+text prompts for robot video generation (tasks and embodiments). MLLM judge scores task completion, physical plausibility, stability.
Wan 2.6 60.7%