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

#ModelScoreOverall rank
1InternVL3-78B43.87#759
2InternVL3-38B42.58#939
3InternVL3-14B42.58#1214
4Qwen 2.5 VL 72B Instruct41.29#841
5Gemini 2.5 Pro40.65#276
6GPT-540.65#178
7Qwen 3 VL 32B Instruct38.71#606
8Qwen 3 VL 32B (Thinking)38.71#573
9Qwen 3 VL 235B A22B Instruct37.42#532
10LLaVA-Video-72B36.77#1193
11Qwen 3 VL 8B Instruct36.13#1029
12LLaVA-OneVision-72B35.48#1771
13Gemini 3.1 Pro (Preview)34.84#99
14Qwen 2.5 VL 32B Instruct34.84#1062
15Qwen 3 VL 4B Instruct34.19#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.