Benchmark Almanac

TrafficImag

Not in model cards

Models edit roadside traffic videos to show a different sequence of events. The evaluator checks routes, interactions, and preservation of the surrounding scene.

Made by
Xiangyu Li and colleagues
Released
September 2026
Kind
Video generation
Level
Everyday
Scored
Graded by people
Answers
Open-ended
Measures
Capability
Language
English
In and out
Text, Images, Video, Code → Images, Video
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Strongest model tested
Gemini 2.5 Pro Jun 2025 #97 on the capability index
Last model added
September 2025
Scores refreshed
November 20th, 2026
14
Entries in its paper, 13 models we track

GPT-Image-2 leads with 90.0 among models released by September 2025 GPT-Image-2 leads with 90.0 among models released by September 2025

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports three tracks with different metrics, so each row uses its first applicable published metric. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

The newest model with a score here came out in September 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 GPT-Image-2 90.0
  2. 2 Gemini 3 Pro Image Preview (nano-banana-pro) 85.0
  3. 3 Gemini 2.5 Pro Jun 2025 83.6
  4. 4 Qwen-Image-2.0-Pro 81.7
  5. 5 Claude Sonnet 4 80.1
  6. 6 GPT-4o Mar 2025 79.2
  7. 7 Gemini 2.5 Flash Sep 2025 77.9
  8. 8 Qwen2.5-VL-32B 75.4
  9. 9 Seedream 5.0 Pro 75.0
  10. 10 InternVL3-14B 69.7
  11. 11 LLaVA-OneVision 7B 64.8
  12. 12 Seedance 2.0 55.0
  13. 13 Sora 2 Pro 43.3
  14. 14 Veo 3.1 Audio 35.0

Source: The TrafficImag paper

#EntryScoreSettingDateSource
1 GPT-Image-2 90.0 Official leaderboard
2 Gemini 3 Pro Image Preview (nano-banana-pro) 85.0 Official leaderboard
3 Gemini 2.5 Pro Jun 2025 83.6 Jun 2025 Official leaderboard
4 Qwen-Image-2.0-Pro 81.7 Official leaderboard
5 Claude Sonnet 4 80.1 May 2025 Official leaderboard
6 GPT-4o Mar 2025 79.2 Mar 2025 Official leaderboard
7 Gemini 2.5 Flash Sep 2025 77.9 Sep 2025 Official leaderboard
8 Qwen2.5-VL-32B 75.4 Mar 2025 Official leaderboard
9 Seedream 5.0 Pro 75.0 Official leaderboard
10 InternVL3-14B 69.7 Apr 2025 Official leaderboard
11 LLaVA-OneVision 7B 64.8 Aug 2024 Official leaderboard
12 Seedance 2.0 55.0 Official leaderboard
13 Sora 2 Pro 43.3 Official leaderboard
14 Veo 3.1 Audio 35.0 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-Image-2 90.0 Official leaderboard
2 Gemini 3 Pro Image Preview (nano-banana-pro) 85.0 Official leaderboard
3 Gemini 2.5 Pro Jun 2025 83.6 Jun 2025 Official leaderboard
4 Qwen-Image-2.0-Pro 81.7 Official leaderboard
5 Claude Sonnet 4 80.1 May 2025 Official leaderboard
6 GPT-4o Mar 2025 79.2 Mar 2025 Official leaderboard
7 Gemini 2.5 Flash Sep 2025 77.9 Sep 2025 Official leaderboard
8 Qwen2.5-VL-32B 75.4 Mar 2025 Official leaderboard
9 Seedream 5.0 Pro 75.0 Official leaderboard
10 InternVL3-14B 69.7 Apr 2025 Official leaderboard
11 LLaVA-OneVision 7B 64.8 Aug 2024 Official leaderboard
12 Sora 2 Pro 43.3 Official leaderboard
13 Veo 3.1 Audio 35.0 Official leaderboard

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Google DeepMind
Benchmark paper Not tested since Sep 2026

Source: The TrafficImag paper

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
In the benchmark’s paper
60.0 65.0 70.0 75.0 80.0 85.0 2025 60.0 65.0 70.0 75.0 80.0 85.0 2025

Source: Official TrafficImag leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Audio and video

All 695 in Audio and video
  • Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy. Qwen 3.8 Max 88.7%
  • LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization. Gemini 4 Argon 91.7%
  • MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy. Qwen 3.8 Max 82.4%
  • MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy. Qwen 3.8 Max 90.8%
  • FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better. Phi-4-multimodal 4.00%
  • VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules. Qwen3.5-Omni-Plus 93.1%

Data audit

7 of 9 checks pass, 2 warnings. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (14 entries).
  • Pass Models scored 13 models we track, plus 1 other entry on its leaderboard.
  • Warning Newest score The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 2.5 Pro (#97).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 13 rows for models we track and 1 other entry at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check