VAHBench
Agents turn short drama briefs into finished videos with specified characters, dialogue, and durations. The evaluator checks completeness, quality, reliability, and accuracy of production reports.
- Made by
- Hongbo Zhang and colleagues
- Released
- November 2026
- Kind
- Video generation
- Level
- University
- Scored
- Graded by a model
- Answers
- Agent task
- Measures
- Capability
- Subject
- Arts
- Language
- English
- Interaction
- Agentic
- Environment
- APIs and tools
- Refresh
- One fixed set
- Run by
- A host
- In views
- Agents, Image, video and 3D generation
- Strongest model tested
- Claude Opus 5 #11 on the capability index
- Last model added
- July 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 5 leads with 51.8 Claude Opus 5 leads with 51.8
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 on its own with several settings, we keep its best. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. Agents built around a model, such as Claude Code + GLM-5.2, are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best.
- 51.8 Claude Opus 5
- 49.3 Claude Code + GLM-5.2
- 46.2 Claude Code + DeepSeek-V4-Flash
- 44.1 gpt-5.6
- 42.0 Hermes + Claude Opus 5
- 41.7 DeepSeek Harness + Claude Opus 5
- 39.9 Hermes + GLM-5.2
- 38.6 Claude Code + OpenMontage + GLM-5.2
- 38.4 OpenClaw + OpenMontage + Claude Opus 5
- 37.8 Claude Code + OpenMontage + Claude Opus 5
- 31.3 Hermes + DeepSeek-V4-Flash
- 31.3 OpenClaw + OpenMontage + GLM-5.2
- 31.1 DeepSeek Harness + GLM-5.2
- 30.0 OpenSquilla + Claude Opus 5
- 29.4 deepseek-v4-vis
- 29.3 OpenSquilla + DeepSeek-V4-Flash
- 28.9 Codex + OpenMontage + Claude Opus 5
- 26.7 DeepSeek Harness + DeepSeek-V4-Flash
- 25.8 OpenClaw + Claude Opus 5
- 25.8 VideoClaw + Claude Opus 5
- 23.6 Codex + OpenMontage + GLM-5.2
- 21.6 OpenSquilla + GLM-5.2
- 18.0 VideoClaw + GLM-5.2
- 17.3 Codex + Claude Opus 5
- 17.1 ViMax + Claude Opus 5
- 14.3 OpenClaw + GLM-5.2
- 11.1 UniVA + Claude Opus 5
- 8.80 ViMax + GLM-5.2
- 8.20 Codex + GLM-5.2
- 7.44 OpenClaw + DeepSeek-V4-Flash
- 6.48 Codex + DeepSeek-V4-Flash
- 5.62 UniVA + GLM-5.2
- 1 Claude Opus 5 51.8
- 2 Claude Code + GLM-5.2 49.3
- 3 Claude Code + DeepSeek-V4-Flash 46.2
- 4 gpt-5.6 44.1
- 5 Hermes + Claude Opus 5 42.0
- 6 DeepSeek Harness + Claude Opus 5 41.7
- 7 Hermes + GLM-5.2 39.9
- 8 Claude Code + OpenMontage + GLM-5.2 38.6
- 9 OpenClaw + OpenMontage + Claude Opus 5 38.4
- 10 Claude Code + OpenMontage + Claude Opus 5 37.8
- 11 Hermes + DeepSeek-V4-Flash 31.3
- 12 OpenClaw + OpenMontage + GLM-5.2 31.3
- 13 DeepSeek Harness + GLM-5.2 31.1
- 14 OpenSquilla + Claude Opus 5 30.0
- 15 deepseek-v4-vis 29.4
- 16 OpenSquilla + DeepSeek-V4-Flash 29.3
- 17 Codex + OpenMontage + Claude Opus 5 28.9
- 18 DeepSeek Harness + DeepSeek-V4-Flash 26.7
- 19 OpenClaw + Claude Opus 5 25.8
- 20 VideoClaw + Claude Opus 5 25.8
- 21 Codex + OpenMontage + GLM-5.2 23.6
- 22 OpenSquilla + GLM-5.2 21.6
- 23 VideoClaw + GLM-5.2 18.0
- 24 Codex + Claude Opus 5 17.3
- 25 ViMax + Claude Opus 5 17.1
- 26 OpenClaw + GLM-5.2 14.3
- 27 UniVA + Claude Opus 5 11.1
- 28 ViMax + GLM-5.2 8.80
- 29 Codex + GLM-5.2 8.20
- 30 OpenClaw + DeepSeek-V4-Flash 7.44
- 31 Codex + DeepSeek-V4-Flash 6.48
- 32 UniVA + GLM-5.2 5.62
Source: The VAHBench paper
- 1 Claude Opus 5 51.8
Source: The VAHBench paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5 | 51.8 | Claude Code | Jul 2026 | Official leaderboard |
| 2 | Claude Code + GLM-5.2 | 49.3 | Jun 2026 | Official leaderboard | |
| 3 | Claude Code + DeepSeek-V4-Flash | 46.2 | Apr 2026 | Official leaderboard | |
| 4 | gpt-5.6 | 44.1 | Claude Code | Official leaderboard | |
| 5 | Hermes + Claude Opus 5 | 42.0 | Jul 2026 | Official leaderboard | |
| 6 | DeepSeek Harness + Claude Opus 5 | 41.7 | Jul 2026 | Official leaderboard | |
| 7 | Hermes + GLM-5.2 | 39.9 | Jun 2026 | Official leaderboard | |
| 8 | Claude Code + OpenMontage + GLM-5.2 | 38.6 | Jun 2026 | Official leaderboard | |
| 9 | OpenClaw + OpenMontage + Claude Opus 5 | 38.4 | Jul 2026 | Official leaderboard | |
| 10 | Claude Code + OpenMontage + Claude Opus 5 | 37.8 | Jul 2026 | Official leaderboard | |
| 11 | Hermes + DeepSeek-V4-Flash | 31.3 | Apr 2026 | Official leaderboard | |
| 12 | OpenClaw + OpenMontage + GLM-5.2 | 31.3 | Jun 2026 | Official leaderboard | |
| 13 | DeepSeek Harness + GLM-5.2 | 31.1 | Jun 2026 | Official leaderboard | |
| 14 | OpenSquilla + Claude Opus 5 | 30.0 | Jul 2026 | Official leaderboard | |
| 15 | deepseek-v4-vis | 29.4 | Claude Code + OpenMontage | Official leaderboard | |
| 16 | OpenSquilla + DeepSeek-V4-Flash | 29.3 | Apr 2026 | Official leaderboard | |
| 17 | Codex + OpenMontage + Claude Opus 5 | 28.9 | Jul 2026 | Official leaderboard | |
| 18 | DeepSeek Harness + DeepSeek-V4-Flash | 26.7 | Apr 2026 | Official leaderboard | |
| 19 | OpenClaw + Claude Opus 5 | 25.8 | Jul 2026 | Official leaderboard | |
| 20 | VideoClaw + Claude Opus 5 | 25.8 | Jul 2026 | Official leaderboard | |
| 21 | Codex + OpenMontage + GLM-5.2 | 23.6 | Jun 2026 | Official leaderboard | |
| 22 | OpenSquilla + GLM-5.2 | 21.6 | Jun 2026 | Official leaderboard | |
| 23 | VideoClaw + GLM-5.2 | 18.0 | Jun 2026 | Official leaderboard | |
| 24 | Codex + Claude Opus 5 | 17.3 | Jul 2026 | Official leaderboard | |
| 25 | ViMax + Claude Opus 5 | 17.1 | Jul 2026 | Official leaderboard | |
| 26 | OpenClaw + GLM-5.2 | 14.3 | Jun 2026 | Official leaderboard | |
| 27 | UniVA + Claude Opus 5 | 11.1 | Jul 2026 | Official leaderboard | |
| 28 | ViMax + GLM-5.2 | 8.80 | Jun 2026 | Official leaderboard | |
| 29 | Codex + GLM-5.2 | 8.20 | Jun 2026 | Official leaderboard | |
| 30 | OpenClaw + DeepSeek-V4-Flash | 7.44 | Apr 2026 | Official leaderboard | |
| 31 | Codex + DeepSeek-V4-Flash | 6.48 | Apr 2026 | Official leaderboard | |
| 32 | UniVA + GLM-5.2 | 5.62 | Jun 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5 | 51.8 | Claude Code | Jul 2026 | 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 VAHBench 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 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 3 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (32 entries).
- Pass Models scored 1 model we track, plus 31 other entries on its leaderboard.
- Pass Newest score The newest is from July 2026, for Claude Opus 5.
- Note Frontier models None of the top 10 has a score. The strongest tested is Claude Opus 5 (#11).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 30 rows for models we track and 2 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.