TrafficImag
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
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision, Image, video and 3D generation
- Strongest model tested
-
Gemini 2.5 Pro Jun 2025 #97 on the capability index
- Last model added
- September 2025
- Scores refreshed
- November 20th, 2026
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:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 90.0 GPT-Image-2
- 85.0
Gemini 3 Pro Image Preview (nano-banana-pro)
- 83.6
Gemini 2.5 Pro
- 81.7
Qwen-Image-2.0-Pro
- 80.1 Claude Sonnet 4
- 79.2 GPT-4o
- 77.9
Gemini 2.5 Flash
- 75.4
Qwen2.5-VL-32B
- 75.0
Seedream 5.0 Pro
- 69.7
InternVL3-14B
- 64.8
LLaVA-OneVision 7B
- 55.0 Seedance 2.0
- 43.3 Sora 2 Pro
- 35.0
Veo 3.1 Audio
- 1 GPT-Image-2 90.0
- 2
Gemini 3 Pro Image Preview (nano-banana-pro) 85.0
- 3
Gemini 2.5 Pro Jun 2025 83.6
- 4
Qwen-Image-2.0-Pro 81.7
- 5 Claude Sonnet 4 80.1
- 6 GPT-4o Mar 2025 79.2
- 7
Gemini 2.5 Flash Sep 2025 77.9
- 8
Qwen2.5-VL-32B 75.4
- 9
Seedream 5.0 Pro 75.0
- 10
InternVL3-14B 69.7
- 11
LLaVA-OneVision 7B 64.8
- 12 Seedance 2.0 55.0
- 13 Sora 2 Pro 43.3
- 14
Veo 3.1 Audio 35.0
Source: The TrafficImag paper
- 1 GPT-Image-2 90.0
- 2
Gemini 3 Pro Image Preview (nano-banana-pro) 85.0
- 3
Gemini 2.5 Pro Jun 2025 83.6
- 4
Qwen-Image-2.0-Pro 81.7
- 5 Claude Sonnet 4 80.1
- 6 GPT-4o Mar 2025 79.2
- 7
Gemini 2.5 Flash Sep 2025 77.9
- 8
Qwen2.5-VL-32B 75.4
- 9
Seedream 5.0 Pro 75.0
- 10
InternVL3-14B 69.7
- 11
LLaVA-OneVision 7B 64.8
- 12 Sora 2 Pro 43.3
- 13
Veo 3.1 Audio 35.0
Source: The TrafficImag paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-Image-2 | 90.0 | Official leaderboard | ||
| 2 | | 85.0 | Official leaderboard | ||
| 3 | | 83.6 | Jun 2025 | Official leaderboard | |
| 4 | | 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 | | 77.9 | Sep 2025 | Official leaderboard | |
| 8 | | 75.4 | Mar 2025 | Official leaderboard | |
| 9 | | 75.0 | Official leaderboard | ||
| 10 | | 69.7 | Apr 2025 | Official leaderboard | |
| 11 | | 64.8 | Aug 2024 | Official leaderboard | |
| 12 | Seedance 2.0 | 55.0 | Official leaderboard | ||
| 13 | Sora 2 Pro | 43.3 | Official leaderboard | ||
| 14 | | 35.0 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-Image-2 | 90.0 | Official leaderboard | ||
| 2 | | 85.0 | Official leaderboard | ||
| 3 | | 83.6 | Jun 2025 | Official leaderboard | |
| 4 | | 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 | | 77.9 | Sep 2025 | Official leaderboard | |
| 8 | | 75.4 | Mar 2025 | Official leaderboard | |
| 9 | | 75.0 | Official leaderboard | ||
| 10 | | 69.7 | Apr 2025 | Official leaderboard | |
| 11 | | 64.8 | Aug 2024 | Official leaderboard | |
| 12 | Sora 2 Pro | 43.3 | Official leaderboard | ||
| 13 | | 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.
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.
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
- 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.