Skip to content

Benchmark

OmniCapBench · Semantic · Subject recall

Scores are percentages. Higher is better.

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

Score distribution

42.4%
Mean
43.8%
Median
6.6%
Std dev
40.3%
10th percentile
46.7%
90th percentile
25.9%
Min
25.9%51.5%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#Model or systemScore
1MiMo 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 docs46.7%
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 docs45.4%
3Qwen3.5 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 docs43.9%
4Gemini 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 docs43.8%

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 docs51.5%
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 docs25.9%
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 docs42%
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 docs40.3%
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 docs42.1%

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.