VideoOdyssey-V - Temporal Grounding: leaderboard
VideoOdyssey (2026) tests ultra-long video understanding with human-written multiple-choice questions on videos averaging 109 minutes, each annotated with how long a viewer must watch continuously to answer. This board is accuracy in percent on the visual subset questions about locating when an event happens; higher is better.
Metric: Multiple-choice accuracy (%) on the 65 temporal grounding questions (locate the specific timestamp in the video where a described visual event occurs) of VideoOdyssey-V (human-written questions on 100 videos of 60 to 255 minutes that need visual cues and long continuous viewing; 1,618 in all), 128 frames for proprietary models and each open model's maximum frame setting; higher is better. Source: arxiv.org. Saturation forecast: Around May 2028. 18 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 49.2 | #99 |
| 2 | Seed 2.0 Pro | 47.7 | #222 |
| 3 | Kimi K2.5 | 46.2 | #266 |
| 4 | GPT-5.2 | 44.6 | #185 |
| 5 | VideoLLaMA3-7B | 43.1 | #2050 |
| 6 | Gemini 2.5 Pro | 40 | #276 |
| 7 | Video-KTR-7B | 40 | |
| 8 | Qwen 3 VL 235B A22B | 38.5 | #485 |
| 9 | InternVL3.5-38B | 36.9 | #1021 |
| 10 | Qwen 3 VL 32B | 36.9 | #622 |
| 11 | Video-R1 | 36.9 | #1379 |
| 12 | LLaVA-OneVision-1.5-8B | 35.4 | #1864 |
| 13 | Kimi-VL-A3B | 32.3 | #2340 |
| 14 | Phi-4 Multimodal Instruct | 29.2 | #4154 |
| 15 | LLaVA-NeXT-Video-DPO (34B) | 26.2 | #2489 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=videoodyssey-v-temporal-grounding · How It Works · Data refreshed daily, snapshot 2026-11-21.