Skip to content

Benchmark

OmniCapBench · Semantic · Subshot precision

Scores are percentages. Higher is better.

Models and systems measured
9
Scores recorded
9
Sources
1
IQ weight
No weight published

Score distribution

64.4%
Mean
67.3%
Median
8.6%
Std dev
55.9%
10th percentile
71.2%
90th percentile
46%
Min
46%72.9%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#Model or systemScore
1Gemini 3.1 Pro PreviewOmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · bounded localized semantic judging on structurally aligned units · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard· Reported by OmniCapBench authors / Tencent Hunyuan· via BenchBoard docs70.9%
2Qwen3.5 Omni PlusOmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · bounded localized semantic judging on structurally aligned units · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard· Reported by OmniCapBench authors / Tencent Hunyuan· via BenchBoard docs70.7%
3MiMo V2.5OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · bounded localized semantic judging on structurally aligned units · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard· Reported by OmniCapBench authors / Tencent Hunyuan· via BenchBoard docs67.3%
4Qwen3.5 Omni FlashOmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · bounded localized semantic judging on structurally aligned units · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard· Reported by OmniCapBench authors / Tencent Hunyuan· via BenchBoard docs67.3%

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
Gemini 2.5 ProOmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · bounded localized semantic judging on structurally aligned units · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard· Reported by OmniCapBench authors / Tencent Hunyuan· via BenchBoard docs71.2%
MiniCPM-o 2.6 (OmniCapBench label)OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · bounded localized semantic judging on structurally aligned units · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard· Reported by OmniCapBench authors / Tencent Hunyuan· via BenchBoard docs55.9%
Qwen3 Omni Captioner (OmniCapBench label)OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · bounded localized semantic judging on structurally aligned units · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard· Reported by OmniCapBench authors / Tencent Hunyuan· via BenchBoard docs46%
Qwen3 Omni Instruct (OmniCapBench label)OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · bounded localized semantic judging on structurally aligned units · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard· Reported by OmniCapBench authors / Tencent Hunyuan· via BenchBoard docs57.8%
Seed2.0 (OmniCapBench label)OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · bounded localized semantic judging on structurally aligned units · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard· Reported by OmniCapBench authors / Tencent Hunyuan· via BenchBoard docs72.9%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.