CoVR-R
Models find the video that matches a reference clip after applying a change described in text.
The correct result must reflect the consequences of the requested change.
- Made by
- Omkar Thawakar and colleagues
- Released
- March 2026
- Kind
- Video understanding
- Level
- School
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision
- Last model added
- January 2025
- Scores refreshed
- November 20th, 2026
Qwen3-VL-72B tops the leaderboard with 55.5% Qwen2.5-VL-7B leads with 47.6%
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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. The best model we track is Qwen2.5-VL-7B, at 47.6%. This view shows only models we track, each at its best.
- 1 Qwen3-VL-72B With reasoning 55.5%
- 2 Qwen3-VL-8B Iterative refinement 50.6%
- 3
Qwen2.5-VL-7B With reasoning 47.6%
- 4 Qwen3-VL-4B With reasoning 44%
- 5
Qwen2.5-VL-3B With reasoning 41.8%
- 6 BSE-CoVR CA fusion, with captions, 15 frames 37.9%
- 7 MVFT-JI CA fusion, with captions, 15 frames 34.4%
- 8 Thawakar et al. Avg fusion, with captions, 15 frames 31.7%
- 9 CoVR-BLIP Avg fusion, without captions, 15 frames 30.3%
Source: The CoVR-R paper
- 1
Qwen2.5-VL-7B With reasoning 47.6%
- 2
Qwen2.5-VL-3B With reasoning 41.8%
Source: The CoVR-R paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Qwen3-VL-72B | 55.5% | With reasoning | Official leaderboard | |
| 2 | Qwen3-VL-8B | 50.6% | Iterative refinement | Official leaderboard | |
| 3 | | 47.6% | With reasoning | Jan 2025 | Official leaderboard |
| 4 | Qwen3-VL-4B | 44% | With reasoning | Official leaderboard | |
| 5 | | 41.8% | With reasoning | Jan 2025 | Official leaderboard |
| 6 | BSE-CoVR | 37.9% | CA fusion, with captions, 15 frames | Official leaderboard | |
| 7 | MVFT-JI | 34.4% | CA fusion, with captions, 15 frames | Official leaderboard | |
| 8 | Thawakar et al. | 31.7% | Avg fusion, with captions, 15 frames | Official leaderboard | |
| 9 | CoVR-BLIP | 30.3% | Avg fusion, without captions, 15 frames | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 47.6% | With reasoning | Jan 2025 | Official leaderboard |
| 2 | | 41.8% | With reasoning | Jan 2025 | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official CoVR-R 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
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 22 months ago, in January 2025, for Qwen2.5-VL-3B. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (9 entries).
- Pass Models scored 2 models we track, plus 7 other entries on its leaderboard.
- Warning Newest score The newest came 22 months ago, in January 2025, for Qwen2.5-VL-3B.
- Note Frontier models None of its models are on the capabilities index.
- Pass Headroom The best is 47.6%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 2 rows for models we track and 7 other entries 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.