Skip to main content
BenchLM
Advertise

Benchmark profile

VideoMMMU

A video extension of MMMU-style multimodal reasoning over expert questions grounded in temporal media.

Data verified

Benchmark score on VideoMMMU — July 23, 2026

BenchLM mirrors the published score view for VideoMMMU. Gemini 3 Pro leads the public snapshot at 87.6% , followed by Kimi K2.5 (86.6%) and Qwen3.7 Plus (85.4%). BenchLM does not use these results to rank models overall.

1Closed

Gemini 3 Pro

Google

gemini-3-pro

87.6%
Overall 67.73Context 2M
2Open

Kimi K2.5

Moonshot AI

kimi-k2-5

86.6%
Overall 59.66Context 256K
3Closed

Qwen3.7 Plus

Alibaba

qwen3-7-plus

85.4%
Overall 67.22Context 1M
9 modelsMultimodal & GroundedCurrentDisplay onlyUpdated July 23, 2026

Benchmark score table (9 models)

Score
1
Gemini 3 ProGoogle · Closed
87.6%
2
Kimi K2.5Moonshot AI · Open weight
86.6%
3
Qwen3.7 PlusAlibaba · Closed
85.4%
4
Qwen3.5 397BAlibaba · Open weight
84.7%
5
MiniMax M3MiniMax · Open weight
84.6%
6
Claude Opus 4.5Anthropic · Closed
84.4%
7
Qwen3.6-27BAlibaba · Open weight
84.4%
8
Qwen3.6 PlusAlibaba · Closed
84.0%
9
Qwen3.6-35B-A3BAlibaba · Open weight
83.7%

The published VideoMMMU snapshot places Gemini 3 Pro first at 87.6%. The third row is 2.2 points behind. The broader top-10 range is 3.9 points, so many of the published results sit in a relatively narrow band.

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

About VideoMMMU

Year

2026

Tasks

Video-grounded expert reasoning

Format

Video + text reasoning

Difficulty

Frontier multimodal video reasoning

VideoMMMU tests whether multimodal reasoning skills extend from static images into temporal video understanding. It is useful for evaluating long-form visual reasoning rather than static scene recognition.

Qwen3.6 launch benchmarks

BenchLM freshness & provenance

Version

VideoMMMU 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.

FAQ

What does VideoMMMU measure?

A video extension of MMMU-style multimodal reasoning over expert questions grounded in temporal media.

Which model scores highest on VideoMMMU?

Gemini 3 Pro by Google currently leads with a score of 87.6% on VideoMMMU.

How many models are evaluated on VideoMMMU?

9 AI models have been evaluated on VideoMMMU on BenchLM.

Compare Top Models on VideoMMMU

Gemini 3 Pro vs Kimi K2.5Kimi K2.5 vs Qwen3.7 PlusQwen3.7 Plus vs Qwen3.5 397BQwen3.5 397B vs MiniMax M3
Last updated: July 23, 2026 · BenchLM version VideoMMMU 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.