Flat-Pack Bench - Temporal Localization: leaderboard
Flat-Pack Bench (2026) Temporal Localization questions (103) on furniture-assembly videos with segmented visual-prompt frames: identify the events just before or after the state shown in the visual prompt. Multiple-choice accuracy in percent, each model scored in its best of six video and prompt settings; higher is better.
Metric: TLoc: identify the events just before or after the state shown in the visual prompt, 103 questions; multiple-choice accuracy (%, regex exact match) on furniture-assembly videos from IMaW with one or two segmented visual-prompt frames, zero-shot with greedy decoding (GPT-5 at its default); each row is the model's best of up to six settings (key-frame or trimmed video, mixed-media, collage or concat visual prompt) chosen by overall micro-average accuracy, the paper's main-table protocol; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 30 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 53.4 | #178 |
| 2 | Qwen 3 VL 32B Instruct | 46.6 | #606 |
| 3 | Gemini 2.5 Pro | 44.66 | #276 |
| 4 | Gemini 3.1 Pro (Preview) | 43.69 | #99 |
| 5 | Gemini 2.5 Flash | 41.75 | #463 |
| 6 | InternVL3-78B | 39.81 | #759 |
| 7 | InternVL3-38B | 37.86 | #939 |
| 8 | Video-LLaVA-7B | 35.92 | #3879 |
| 9 | Qwen 3 VL 4B Instruct | 33.01 | #1332 |
| 10 | Qwen 3 VL 8B (Thinking) | 33.01 | #910 |
| 11 | Perception-LM-3B | 32.04 | |
| 12 | Qwen 3 VL 8B Instruct | 30.1 | #1029 |
| 13 | Qwen 2.5 VL 72B Instruct | 30.1 | #841 |
| 14 | LLaVA-OneVision-7B | 30.1 | #2981 |
| 15 | Flat-Pack Bench VideoRefer (checkpoint unspecified) | 30.1 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=flat-pack-bench-temporal-localization · How It Works · Data refreshed daily, snapshot 2026-11-21.