VideoJev Evaluation - MLVU development MCQ: leaderboard
VideoJev Evaluation - MLVU development MCQ. Table2 source protocol; VideoJev Joint inference; Instruct and Thinking checkpoints/runs preserved. Molmo2 32K context and Nemotron128K context. Missing source cells retained as absent. Metric: Accuracy (%). Primary published table; source configurations remain distinct.
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Around January 2027. 19 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.6 35B A3B (Thinking) | 86.2 | #217 (Qwen 3.6 35B A3B) |
| 2 | GPT-5.2 | 85.6 | #109 |
| 3 | Qwen 3.5 35B A3B (Thinking) | 85.6 | #250 (Qwen 3.5 35B A3B) |
| 4 | Gemini 3 Pro | 83 | #77 |
| 5 | Qwen 3.5 4B (Thinking) | 82.8 | #463 (Qwen 3.5 4B) |
| 6 | Claude Opus 4.5 | 81.7 | #81 |
| 7 | Qwen 3 VL 30B A3B (Thinking) | 78.9 | #341 (Qwen 3 VL 30B A3B) |
| 8 | Qwen 3 VL 4B (Thinking) | 75.7 | #469 (Qwen 3 VL 4B) |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=videojev-evaluation-mlvu-development-mcq · How It Works · Data refreshed daily, snapshot 2026-10-16.