MindCube
ReportedNo description yet: we only describe an eval set when we can do it correctly.
- Kind
- Published by a third party's leaderboard, collected by Epoch AI. The leaderboard is named and linked.
- Link
- https://mind-cube.github.io/
- Score shown
- Epoch's column "Overall score", as a percentage, higher is better. The source gives no error bars.
- Results
- 5 in all: 1 for open-weight models, 1 for closed ones, 3 where Epoch does not say. 1 linked to a model page here.
Best open-weight result: google/gemma-3-12b-it, 46.7%, number 1 of 5 results.
| # | Model | Weights | Setting | Score | Date | Source |
|---|---|---|---|---|---|---|
| 1 | google/gemma-3-12b-itEpoch: gemma-3-12b-it, Google DeepMind | open | default | 46.7% | not dated | mind-cube.github.io |
| 2 | mPLUG-Owl3-7B-241101 | not stated | default | 44.9% | not dated | mind-cube.github.io |
| 3 | claude-sonnet-4-20250514_unknownAnthropic | closed | effort unknown | 44.8% | not dated | mind-cube.github.io |
| 4 | LLaVA-Video-7B-Qwen2 | not stated | default | 42.0% | not dated | mind-cube.github.io |
| 5 | LongVA-7B | not stated | default | 29.5% | not dated | mind-cube.github.io |
Open-weight rows are shaded. Dates are when the result was run or evaluated, where the data says. Data from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Epoch AI. Method