Mindcube

Models scored

5

Best score

0.47

Metric

Overall score

Mindcube is an AI evaluation tracked by Epoch AI, with 5 scored model versions on record. The scores here are reported by third parties rather than produced by Epoch AI running the evaluation itself.

Scored models span June 2024 to May 2025. The best score recorded is 0.47, measured as Overall score. Models come from Google DeepMind, Anthropic.

Full record

Score metric: Overall score
Models scored: 5
Best score recorded: 0.47
Earliest model scored: Jun 13, 2024
Most recent model scored: May 22, 2025
Third-party reported: Yes

Leaderboard

01	gemma-3-12b-it	Google DeepMind	0.47
02	mPLUG-Owl3-7B-241101		0.45
03	claude-sonnet-4-20250514_unknown	Anthropic	0.45
04	LLaVA-Video-7B-Qwen2		0.42
05	LongVA-7B		0.29

More benchmarks

Epoch Capabilities Index MMLU Terminal-Bench GPQA Diamond OTIS Mock AIME 2024-2025 GSM8K ARC-AGI ARC-AGI-2

SourceEpoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/benchmarks. Licensed under CC BY 4.0.

← All benchmarks