Skip to content

Benchmark

OmniCapBench · Semantic · Subject precision

Scores are percentages. Higher is better.

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

Score distribution

61.3%
Mean
62.8%
Median
4.7%
Std dev
57.1%
10th percentile
65.6%
90th percentile
51%
Min
51%67.1%
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 docs67.1%
2Qwen3.5 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 docs65.6%
3Qwen3.5 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 docs62.8%
4MiMo 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 docs58.6%

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 docs57.1%
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 docs63.9%
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 docs51%
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 docs62%
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 docs63.7%

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.