Flat-Pack Bench - Temporal Ordering: leaderboard
Flat-Pack Bench (2026) Temporal Ordering questions (155) on furniture-assembly videos with segmented visual-prompt frames: order the connection events of the highlighted parts. Multiple-choice accuracy in percent, each model scored in its best of six video and prompt settings; higher is better.
Metric: TOrd: order the connection events of the highlighted parts, 155 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 2032. 30 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | InternVL3-78B | 43.87 | #759 |
| 2 | InternVL3-38B | 42.58 | #939 |
| 3 | InternVL3-14B | 42.58 | #1214 |
| 4 | Qwen 2.5 VL 72B Instruct | 41.29 | #841 |
| 5 | Gemini 2.5 Pro | 40.65 | #276 |
| 6 | GPT-5 | 40.65 | #178 |
| 7 | Qwen 3 VL 32B Instruct | 38.71 | #606 |
| 8 | Qwen 3 VL 32B (Thinking) | 38.71 | #573 |
| 9 | Qwen 3 VL 235B A22B Instruct | 37.42 | #532 |
| 10 | LLaVA-Video-72B | 36.77 | #1193 |
| 11 | Qwen 3 VL 8B Instruct | 36.13 | #1029 |
| 12 | LLaVA-OneVision-72B | 35.48 | #1771 |
| 13 | Gemini 3.1 Pro (Preview) | 34.84 | #99 |
| 14 | Qwen 2.5 VL 32B Instruct | 34.84 | #1062 |
| 15 | Qwen 3 VL 4B Instruct | 34.19 | #1332 |
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-ordering · How It Works · Data refreshed daily, snapshot 2026-11-21.