Skip to main content

Video-MME with subtitle (Video-MME (with subtitle))

A video understanding benchmark that allows subtitle access when answering multimodal questions about videos.

How BenchLM shows Video-MME (with subtitle) right now

BenchLM is tracking Video-MME (with subtitle) in the local dataset, but exact-source verification records for these rows are still being attached. To avoid a blank benchmark page, BenchLM shows the current tracked rows below as a display-only reference table.

These tracked rows are useful for inspection and spot-checking, but until exact-source attachments are completed they should not be treated as fully verified public benchmark rows.

6 tracked modelsLocal tracked rowsAwaiting exact-source attachmentsDisplay only

Tracked score on Video-MME (with subtitle) — April 10, 2026

BenchLM mirrors the published tracked score view for Video-MME (with subtitle). Gemini 3 Pro leads the public snapshot at 88.4% , followed by Qwen3.6 Plus (87.8%) and Qwen3.5 397B (87.5%). BenchLM does not use these results to rank models overall.

6 modelsMultimodal & GroundedCurrentDisplay onlyUpdated April 10, 2026

The published Video-MME (with subtitle) snapshot is tightly clustered at the top: Gemini 3 Pro sits at 88.4%, while the third row is only 0.9 points behind. The broader top-10 spread is 10.8 points, so the benchmark still separates strong models even when the leaders cluster.

6 models have been evaluated on Video-MME (with subtitle). The benchmark falls in the Multimodal & Grounded category. This category carries a 12% weight in BenchLM.ai's overall scoring system. Video-MME (with subtitle) is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About Video-MME (with subtitle)

Year

2026

Tasks

Video understanding

Format

Video QA with subtitle context

Difficulty

Multimodal video reasoning

The subtitle-enabled Video-MME setting measures how well a model combines video perception with textual cues from subtitles rather than relying on frames alone.

BenchLM freshness & provenance

Version

Video-MME (with subtitle) 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Tracked score table (6 models)

1
Gemini 3 Progemini-3-pro
88.4%
2
Qwen3.6 Plusqwen3-6-plus
87.8%
3
Qwen3.5 397Bqwen3-5-397b
87.5%
4
Kimi K2.5kimi-k2-5
87.4%
5
GPT-5.2gpt-5-2
86.0%
6
Claude Opus 4.5claude-opus-4-5
77.6%

FAQ

What does Video-MME (with subtitle) measure?

A video understanding benchmark that allows subtitle access when answering multimodal questions about videos.

Which model leads the published Video-MME (with subtitle) snapshot?

Gemini 3 Pro currently leads the published Video-MME (with subtitle) snapshot with a tracked score of 88.4%. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on Video-MME (with subtitle)?

6 AI models are included in BenchLM's mirrored Video-MME (with subtitle) snapshot, based on the public leaderboard captured on April 10, 2026.

Last updated: April 10, 2026 · mirrored from the public benchmark leaderboard

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.