MultiHaystack - Contextual Understanding: leaderboard
Metric: Answer accuracy (%) on the contextual understanding questions (30 of 747), where the model answers from the top-5 items that the E5-V retriever returns from MultiHaystack's 46,260-item mixed corpus of images, videos and documents, graded correct or incorrect by a GPT-4o-mini judge; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 56.67 | #91 |
| 2 | Gemini 2.5 Flash | 46.67 | #237 |
| 3 | InternVL3-8B | 23.33 | #606 |
| 4 | Qwen 2 VL 7B | 23.33 | #741 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=multihaystack-contextual-understanding · How It Works · Data refreshed daily, snapshot 2026-10-11.