Multimodal · Benchmark profile

Multimodal Multi-disciplinary Video Understanding

A benchmark for evaluating multimodal models on video understanding tasks across multiple disciplines, emphasizing temporal reasoning and comprehension over video content.

Reference2026Active4 models

Data verified 1 Aug 2026 · Methodology 2.3.0

Benchmark score on Multimodal Multi-disciplinary Video Understanding

Leaderboard · 4 models

Kimi K2.5 leads at 80.4%, followed by Qwen3.5-122B-A10B (74.7%) and Qwen3.5 27B (73.3%).

Display onlyMultimodal2026

#1Open

Kimi K2.5

Moonshot AI

kimi-k2.5

80.4%

Overall #53 · Context 256K tokens

#2Open

Qwen3.5-122B-A10B

Alibaba Cloud

Qwen/Qwen3.5-122B-A10B

74.7%

Overall #70 · Context 262K tokens

#3Open

Qwen3.5 27B

Alibaba Cloud

qwen3.5-27b

73.3%

Overall #74 · Context 262K tokens

ViewModelsColours

Moonshot AIAlibaba Cloud

Lumina

Multimodal Multi-disciplinary Video Understanding leaderboard

Accessible data for Multimodal Multi-disciplinary Video Understanding leaderboard
Model	Rank	Model ID	Provider	Score	Unit
Kimi K2.5	#1	kimi-k2-5	Moonshot AI	80.4	percent
Qwen3.5-122B-A10B	#2	qwen3-5-122b-a10b	Alibaba Cloud	74.7	percent
Qwen3.5 27B	#3	qwen3-5-27b	Alibaba Cloud	73.3	percent
Qwen3.5-35B-A3B	#4	qwen3-5-35b-a3b	Alibaba Cloud	72.3	percent

Benchmark score table (4 models)

One best compatible score per canonical product · higher is better

Multimodal Multi-disciplinary Video Understanding leaderboard ranked by score
Rank	Model	Provider	License	Evidence use	Score
#1	Kimi K2.5 kimi-k2.5	Moonshot AI	open	Source carrier	80.4%
#2	Qwen3.5-122B-A10B Qwen/Qwen3.5-122B-A10B	Alibaba Cloud	open	Source carrier	74.7%
#3	Qwen3.5 27B qwen3.5-27b	Alibaba Cloud	open	Source carrier	73.3%
#4	Qwen3.5-35B-A3B qwen3-5-35b-a3b	Alibaba Cloud	open	Source carrier	72.3%

The top of this snapshot is led by Kimi K2.5 at 80.4%; third place is 7.1 points behind. The top-4 spread is 8.1 points.

Configuration-preserving evidencePublished source rows (12)Exact source labels, configurations, versions and dated observations. Same-snapshot canonical/configuration projections are shown once.

Every distinct dated source-published row for Multimodal Multi-disciplinary Video Understanding, including exact model configuration labels
Exact published model / configuration	Canonical product	Score	Version / system	Evidence	Source / observed
Exact BenchLM registry variant Kimi K2.5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K2.5	80.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen3.5-122B-A10B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5-122B-A10B	74.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen3.5-27B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5 27B	73.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen3.5-35B-A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5-35B-A3B	72.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Kimi K2.5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K2.5	80.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen3.5-122B-A10B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5-122B-A10B	74.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen3.5-27B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5 27B	73.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen3.5-35B-A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5-35B-A3B	72.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Kimi K2.5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K2.5	80.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Qwen3.5-122B-A10B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5-122B-A10B	74.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Qwen3.5-27B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5 27B	73.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Qwen3.5-35B-A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5-35B-A3B	72.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Compare top models

Kimi K2.5 vs Qwen3.5-122B-A10B Qwen3.5-122B-A10B vs Qwen3.5 27B Qwen3.5 27B vs Qwen3.5-35B-A3B

About Multimodal Multi-disciplinary Video Understanding

Definition and scoring

Organisation: MMVU benchmark maintainers
Category: Multimodal
Version: 2026
Direction: higher is better
Ranking use: Reference
Contamination risk: Unknown

A benchmark for evaluating multimodal models on video understanding tasks across multiple disciplines, emphasizing temporal reasoning and comprehension over video content. Every genuine source row stays tied to its exact model label, configuration, benchmark version and evaluation system. The summary chart shows one best compatible score per canonical product; Score 2.0 admits only explicitly mapped, frozen protocols and keeps incompatible configurations separate.

Open benchmark source ↗

FAQ

Quick answers

What does Multimodal Multi-disciplinary Video Understanding measure?

A benchmark for evaluating multimodal models on video understanding tasks across multiple disciplines, emphasizing temporal reasoning and comprehension over video content.

Which model scores highest on Multimodal Multi-disciplinary Video Understanding?

Kimi K2.5 by Moonshot AI currently leads with 80.4%.

How many models are evaluated on Multimodal Multi-disciplinary Video Understanding?

4 canonical model products have a qualifying score, backed by 12 distinct dated source rows.

Does this affect overall Lumina rank?

No. This benchmark is display-only and does not enter the overall Lumina composite.

Multimodal · Benchmark profile

Multimodal Multi-disciplinary Video Understanding

A benchmark for evaluating multimodal models on video understanding tasks across multiple disciplines, emphasizing temporal reasoning and comprehension over video content.

Reference2026Active4 models

Data verified 1 Aug 2026 · Methodology 2.3.0

Benchmark score on Multimodal Multi-disciplinary Video Understanding

Leaderboard · 4 models

Kimi K2.5 leads at 80.4%, followed by Qwen3.5-122B-A10B (74.7%) and Qwen3.5 27B (73.3%).

Display onlyMultimodal2026

#1Open

Kimi K2.5

Moonshot AI

kimi-k2.5

80.4%

Overall #53 · Context 256K tokens

#2Open

Qwen3.5-122B-A10B

Alibaba Cloud

Qwen/Qwen3.5-122B-A10B

74.7%

Overall #70 · Context 262K tokens

#3Open

Qwen3.5 27B

Alibaba Cloud

qwen3.5-27b

73.3%

Overall #74 · Context 262K tokens

ViewModelsColours

Moonshot AIAlibaba Cloud

Lumina

Multimodal Multi-disciplinary Video Understanding leaderboard

Accessible data for Multimodal Multi-disciplinary Video Understanding leaderboard
Model	Rank	Model ID	Provider	Score	Unit
Kimi K2.5	#1	kimi-k2-5	Moonshot AI	80.4	percent
Qwen3.5-122B-A10B	#2	qwen3-5-122b-a10b	Alibaba Cloud	74.7	percent
Qwen3.5 27B	#3	qwen3-5-27b	Alibaba Cloud	73.3	percent
Qwen3.5-35B-A3B	#4	qwen3-5-35b-a3b	Alibaba Cloud	72.3	percent

Benchmark score table (4 models)

One best compatible score per canonical product · higher is better

Multimodal Multi-disciplinary Video Understanding leaderboard ranked by score
Rank	Model	Provider	License	Evidence use	Score
#1	Kimi K2.5 kimi-k2.5	Moonshot AI	open	Source carrier	80.4%
#2	Qwen3.5-122B-A10B Qwen/Qwen3.5-122B-A10B	Alibaba Cloud	open	Source carrier	74.7%
#3	Qwen3.5 27B qwen3.5-27b	Alibaba Cloud	open	Source carrier	73.3%
#4	Qwen3.5-35B-A3B qwen3-5-35b-a3b	Alibaba Cloud	open	Source carrier	72.3%

The top of this snapshot is led by Kimi K2.5 at 80.4%; third place is 7.1 points behind. The top-4 spread is 8.1 points.

Configuration-preserving evidencePublished source rows (12)Exact source labels, configurations, versions and dated observations. Same-snapshot canonical/configuration projections are shown once.

Every distinct dated source-published row for Multimodal Multi-disciplinary Video Understanding, including exact model configuration labels
Exact published model / configuration	Canonical product	Score	Version / system	Evidence	Source / observed
Exact BenchLM registry variant Kimi K2.5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K2.5	80.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen3.5-122B-A10B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5-122B-A10B	74.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen3.5-27B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5 27B	73.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen3.5-35B-A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5-35B-A3B	72.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Kimi K2.5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K2.5	80.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen3.5-122B-A10B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5-122B-A10B	74.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen3.5-27B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5 27B	73.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen3.5-35B-A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5-35B-A3B	72.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Kimi K2.5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K2.5	80.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Qwen3.5-122B-A10B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5-122B-A10B	74.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Qwen3.5-27B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5 27B	73.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Qwen3.5-35B-A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5-35B-A3B	72.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Compare top models

Kimi K2.5 vs Qwen3.5-122B-A10B Qwen3.5-122B-A10B vs Qwen3.5 27B Qwen3.5 27B vs Qwen3.5-35B-A3B

About Multimodal Multi-disciplinary Video Understanding

Definition and scoring

Organisation: MMVU benchmark maintainers
Category: Multimodal
Version: 2026
Direction: higher is better
Ranking use: Reference
Contamination risk: Unknown

Open benchmark source ↗

FAQ

Quick answers

What does Multimodal Multi-disciplinary Video Understanding measure?

A benchmark for evaluating multimodal models on video understanding tasks across multiple disciplines, emphasizing temporal reasoning and comprehension over video content.

Which model scores highest on Multimodal Multi-disciplinary Video Understanding?

Kimi K2.5 by Moonshot AI currently leads with 80.4%.

How many models are evaluated on Multimodal Multi-disciplinary Video Understanding?

4 canonical model products have a qualifying score, backed by 12 distinct dated source rows.

Does this affect overall Lumina rank?

No. This benchmark is display-only and does not enter the overall Lumina composite.

Navigation

Multimodal Multi-disciplinary Video Understanding

Leaderboard · 4 models

Kimi K2.5

Qwen3.5-122B-A10B

Qwen3.5 27B

Multimodal Multi-disciplinary Video Understanding leaderboard

Crop Multimodal Multi-disciplinary Video Understanding leaderboard

Benchmark score table (4 models)

Crop Multimodal Multi-disciplinary Video Understanding benchmark table

Crop Multimodal Multi-disciplinary Video Understanding published source rows

Compare top models

Definition and scoring

Quick answers

What does Multimodal Multi-disciplinary Video Understanding measure?

Which model scores highest on Multimodal Multi-disciplinary Video Understanding?

How many models are evaluated on Multimodal Multi-disciplinary Video Understanding?

Does this affect overall Lumina rank?

Multimodal Multi-disciplinary Video Understanding

Leaderboard · 4 models

Kimi K2.5

Qwen3.5-122B-A10B

Qwen3.5 27B

Multimodal Multi-disciplinary Video Understanding leaderboard

Crop Multimodal Multi-disciplinary Video Understanding leaderboard

Benchmark score table (4 models)

Crop Multimodal Multi-disciplinary Video Understanding benchmark table

Crop Multimodal Multi-disciplinary Video Understanding published source rows

Compare top models

Definition and scoring

Quick answers

What does Multimodal Multi-disciplinary Video Understanding measure?

Which model scores highest on Multimodal Multi-disciplinary Video Understanding?

How many models are evaluated on Multimodal Multi-disciplinary Video Understanding?

Does this affect overall Lumina rank?

Leaderboard · 4 models

Kimi K2.5

Qwen3.5-122B-A10B

Qwen3.5 27B

Benchmark score table (4 models)

Compare top models

Definition and scoring

Quick answers

What does Multimodal Multi-disciplinary Video Understanding measure?

Which model scores highest on Multimodal Multi-disciplinary Video Understanding?

How many models are evaluated on Multimodal Multi-disciplinary Video Understanding?

Does this affect overall Lumina rank?

More Multimodal benchmarks

Leaderboard · 4 models

Kimi K2.5

Qwen3.5-122B-A10B

Qwen3.5 27B

Benchmark score table (4 models)

Compare top models

Definition and scoring

Quick answers

What does Multimodal Multi-disciplinary Video Understanding measure?

Which model scores highest on Multimodal Multi-disciplinary Video Understanding?

How many models are evaluated on Multimodal Multi-disciplinary Video Understanding?

Does this affect overall Lumina rank?

More Multimodal benchmarks