MediaPerf
Models tag and summarize video advertisements. The benchmark measures tag accuracy, summary quality, cost and throughput.
The September release uses 2,003 videos. It scores tagging with macro F1 and grades summaries with a model.
- Made by
- Coactive AI
- Released
- March 2026
- Kind
- Video understanding
- Level
- University
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Subject
- Media and communications
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- New versions replace it
- Run by
- Anyone
- In views
- Vision
- Strongest model tested
- GPT-5.4 #28 on the capability index
- Last model added
- April 2026
- Scores refreshed
- November 20th, 2026
GPT-5.4 leads with 0.42 among models released by April 2026 GPT-5.4 leads with 0.42 among models released by April 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. The default Video Tagging table ranks models by macro F1 on the 68 core tags. 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 April 2026, 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
- 0.42 GPT-5.4
- 0.41
Gemini 3.1 Flash-Lite
- 0.41 Claude Opus 4.6
- 0.39 GPT-5.1
- 0.39
Gemini 3.1 Pro
- 0.38 Claude Sonnet 4.6
- 0.38
Nova 2 Lite
- 0.37 GPT-5 mini
- 0.37 Claude Haiku 4.5
- 0.34
Gemini 2.5 Pro
- 0.34
Gemini 3 Pro
- 0.31
Nemotron 3 Nano Omni 30B-A3B
- 0.31
Qwen3-VL-30B-A3B-Instruct
- 0.30
Nemotron Nano 12B v2 VL
- 0.30 Pegasus 1.2
- 0.27 GPT-5 nano
- 0.25
Amazon Nova Pro
- 1 GPT-5.4 0.42
- 2
Gemini 3.1 Flash-Lite 0.41
- 3 Claude Opus 4.6 0.41
- 4 GPT-5.1 0.39
- 5
Gemini 3.1 Pro 0.39
- 6 Claude Sonnet 4.6 0.38
- 7
Nova 2 Lite 0.38
- 8 GPT-5 mini 0.37
- 9 Claude Haiku 4.5 0.37
- 10
Gemini 2.5 Pro Jun 2025 0.34
- 11
Gemini 3 Pro 0.34
- 12
Nemotron 3 Nano Omni 30B-A3B FP8 0.31
- 13
Qwen3-VL-30B-A3B-Instruct FP8 0.31
- 14
Nemotron Nano 12B v2 VL 0.30
- 15 Pegasus 1.2 0.30
- 16 GPT-5 nano 0.27
- 17
Amazon Nova Pro 0.25
Source: Official MediaPerf leaderboard
- 0.42 GPT-5.4
- 0.41
Gemini 3.1 Flash-Lite
- 0.41 Claude Opus 4.6
- 0.39 GPT-5.1
- 0.39
Gemini 3.1 Pro
- 0.38 Claude Sonnet 4.6
- 0.38
Nova 2 Lite
- 0.37 GPT-5 mini
- 0.37 Claude Haiku 4.5
- 0.34
Gemini 2.5 Pro
- 0.34
Gemini 3 Pro
- 0.31
Nemotron 3 Nano Omni 30B-A3B
- 0.31
Qwen3-VL-30B-A3B-Instruct
- 0.30
Nemotron Nano 12B v2 VL
- 0.27 GPT-5 nano
- 0.25
Amazon Nova Pro
- 1 GPT-5.4 0.42
- 2
Gemini 3.1 Flash-Lite 0.41
- 3 Claude Opus 4.6 0.41
- 4 GPT-5.1 0.39
- 5
Gemini 3.1 Pro 0.39
- 6 Claude Sonnet 4.6 0.38
- 7
Nova 2 Lite 0.38
- 8 GPT-5 mini 0.37
- 9 Claude Haiku 4.5 0.37
- 10
Gemini 2.5 Pro Jun 2025 0.34
- 11
Gemini 3 Pro 0.34
- 12
Nemotron 3 Nano Omni 30B-A3B FP8 0.31
- 13
Qwen3-VL-30B-A3B-Instruct FP8 0.31
- 14
Nemotron Nano 12B v2 VL 0.30
- 15 GPT-5 nano 0.27
- 16
Amazon Nova Pro 0.25
Source: Official MediaPerf leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.4 | 0.42 | Mar 2026 | Official leaderboard | |
| 2 | | 0.41 | Mar 2026 | Official leaderboard | |
| 3 | Claude Opus 4.6 | 0.41 | Feb 2026 | Official leaderboard | |
| 4 | GPT-5.1 | 0.39 | Nov 2025 | Official leaderboard | |
| 5 | | 0.39 | Feb 2026 | Official leaderboard | |
| 6 | Claude Sonnet 4.6 | 0.38 | Feb 2026 | Official leaderboard | |
| 7 | | 0.38 | Dec 2025 | Official leaderboard | |
| 8 | GPT-5 mini | 0.37 | Aug 2025 | Official leaderboard | |
| 9 | Claude Haiku 4.5 | 0.37 | Oct 2025 | Official leaderboard | |
| 10 | | 0.34 | Jun 2025 | Official leaderboard | |
| 11 | | 0.34 | Nov 2025 | Official leaderboard | |
| 12 | | 0.31 | FP8 | Apr 2026 | Official leaderboard |
| 13 | | 0.31 | FP8 | Oct 2025 | Official leaderboard |
| 14 | | 0.30 | Oct 2025 | Official leaderboard | |
| 15 | Pegasus 1.2 closed weights | 0.30 | Official leaderboard | ||
| 16 | GPT-5 nano | 0.27 | Aug 2025 | Official leaderboard | |
| 17 | | 0.25 | Dec 2024 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.4 | 0.42 | Mar 2026 | Official leaderboard | |
| 2 | | 0.41 | Mar 2026 | Official leaderboard | |
| 3 | Claude Opus 4.6 | 0.41 | Feb 2026 | Official leaderboard | |
| 4 | GPT-5.1 | 0.39 | Nov 2025 | Official leaderboard | |
| 5 | | 0.39 | Feb 2026 | Official leaderboard | |
| 6 | Claude Sonnet 4.6 | 0.38 | Feb 2026 | Official leaderboard | |
| 7 | | 0.38 | Dec 2025 | Official leaderboard | |
| 8 | GPT-5 mini | 0.37 | Aug 2025 | Official leaderboard | |
| 9 | Claude Haiku 4.5 | 0.37 | Oct 2025 | Official leaderboard | |
| 10 | | 0.34 | Jun 2025 | Official leaderboard | |
| 11 | | 0.34 | Nov 2025 | Official leaderboard | |
| 12 | | 0.31 | FP8 | Apr 2026 | Official leaderboard |
| 13 | | 0.31 | FP8 | Oct 2025 | Official leaderboard |
| 14 | | 0.30 | Oct 2025 | Official leaderboard | |
| 15 | GPT-5 nano | 0.27 | Aug 2025 | Official leaderboard | |
| 16 | | 0.25 | Dec 2024 | Official leaderboard |
Rankings by part
We read 3 parts from the benchmark’s own leaderboard: Video Tagging: Core dataset, Video Tagging: Extended dataset and Video Summarization: Core dataset. Each ranks models on one part of the test. GPT-5.4 leads 1 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
Video Tagging: Core dataset
16 models we track have a score here.
- 1 GPT-5.4 0.42
- 2
Gemini 3.1 Flash-Lite 0.41
- 3 Claude Opus 4.6 0.41
- 4 GPT-5.1 0.39
- 5
Gemini 3.1 Pro 0.39
- 6 Claude Sonnet 4.6 0.38
- 7
Nova 2 Lite 0.38
- 8 GPT-5 mini 0.37
- 9 Claude Haiku 4.5 0.37
- 10
Gemini 2.5 Pro Jun 2025 0.34
Video Tagging: Extended dataset
15 models we track have a score here.
- 1 Claude Opus 4.6 ↑2 0.56
- 2
Gemini 3.1 Pro ↑3 0.56
- 3
Gemini 2.5 Pro Jun 2025 ↑7 0.55
- 4 GPT-5.1 0.54
- 5 GPT-5.4 ↓4 0.54
- 6 Claude Sonnet 4.6 0.51
- 7 Claude Haiku 4.5 ↑2 0.45
- 8
Gemini 3.1 Flash-Lite ↓6 0.45
- 9 GPT-5 mini ↓1 0.42
- 10
Nova 2 Lite ↓3 0.42
Video Summarization: Core dataset
16 models we track have a score here.
- 1
Gemini 3.1 Pro ↑4 14.4
- 2
Gemini 2.5 Pro Jun 2025 ↑8 14.3
- 3 GPT-5.4 ↓2 14.2
- 4
Gemini 3 Pro ↑7 14.2
- 5 GPT-5.1 ↓1 14.0
- 6
Gemini 3.1 Flash-Lite ↓4 13.6
- 7 GPT-5 mini ↑1 13.6
- 8 Claude Opus 4.6 ↓5 12.3
- 9 GPT-5 nano ↑6 12.3
- 10
Qwen3-VL-30B-A3B-Instruct ↑3 12.2
Quality vs. Cost
The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.
| Model | Setting | F1 (macro) | Cost per hour of video |
|---|---|---|---|
| GPT-5.4 | 0.42 | $7.34 | |
| 0.41 | $0.14 | ||
| Claude Opus 4.6 | 0.41 | $10.92 | |
| GPT-5.1 | 0.39 | $2.04 | |
| 0.39 | $2.11 | ||
| Claude Sonnet 4.6 | 0.38 | $6.57 | |
| 0.38 | $0.54 | ||
| GPT-5 mini | 0.37 | $0.64 | |
| Claude Haiku 4.5 | 0.37 | $2.42 | |
| 0.35 | $2.13 | ||
| 0.34 | $3 | ||
| FP8 | 0.31 | $0.88 | |
| FP8 | 0.31 | $0.68 | |
| 0.3 | $1.11 | ||
| Pegasus 1.2 | 0.3 | $1.85 | |
| GPT-5 nano | 0.27 | $0.18 | |
| 0.25 | $1.37 |
Quality vs. Cost
The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.
| Model | Setting | F1 (macro) | Cost per hour of video |
|---|---|---|---|
| GPT-5.4 | 0.42 | $7.34 | |
| 0.41 | $0.14 | ||
| Claude Opus 4.6 | 0.41 | $10.92 | |
| GPT-5.1 | 0.39 | $2.04 | |
| 0.39 | $2.11 | ||
| Claude Sonnet 4.6 | 0.38 | $6.57 | |
| 0.38 | $0.54 | ||
| GPT-5 mini | 0.37 | $0.64 | |
| Claude Haiku 4.5 | 0.37 | $2.42 | |
| 0.35 | $2.13 | ||
| 0.34 | $3 | ||
| FP8 | 0.31 | $0.88 | |
| FP8 | 0.31 | $0.68 | |
| 0.3 | $1.11 | ||
| GPT-5 nano | 0.27 | $0.18 | |
| 0.25 | $1.37 |
3 models have held number one on the official leaderboard since its release in March 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official MediaPerf 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 MediaPerf 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
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 7 months ago, in April 2026, for Nemotron 3 Nano Omni 30B-A3B. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (17 entries).
- Pass Models scored 16 models we track, plus 1 other entry on its leaderboard.
- Warning Newest score The newest came 7 months ago, in April 2026, for Nemotron 3 Nano Omni 30B-A3B.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.4 (#28).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on mediaperf.org: 16 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.