Multimodal · Benchmark profile
A benchmark for evaluating multimodal models on video understanding tasks across multiple disciplines, emphasizing temporal reasoning and comprehension over video content.
Data verified 21 Jul 2026 · Methodology 1.6.0
Benchmark score on Multimodal Multi-disciplinary Video Understanding
Kimi K2.5 leads at 80.4%, followed by Qwen3.5-122B-A10B (74.7%) and Qwen3.5 27B (73.3%).
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
4 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| Kimi K2.5 | #1 | Moonshot AI | 80.4% |
| Qwen3.5-122B-A10B | #2 | Alibaba Cloud | 74.7% |
| Qwen3.5 27B | #3 | Alibaba Cloud | 73.3% |
| Qwen3.5-35B-A3B | #4 | Alibaba Cloud | 72.3% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | Kimi K2.5 kimi-k2.5 | Moonshot AI | — | Reference only | 80.4% |
| #2 | Qwen3.5-122B-A10B qwen3-5-122b-a10b | Alibaba Cloud | open | Reference only | 74.7% |
| #3 | Qwen3.5 27B qwen3.5-27b | Alibaba Cloud | open | Reference only | 73.3% |
| #4 | Qwen3.5-35B-A3B qwen3-5-35b-a3b | Alibaba Cloud | open | Reference only | 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.
About 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. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
A benchmark for evaluating multimodal models on video understanding tasks across multiple disciplines, emphasizing temporal reasoning and comprehension over video content.
Kimi K2.5 by Moonshot AI currently leads with 80.4%.
4 models in the LuminaBench cohort have a qualifying score on this benchmark.
No. This benchmark is display-only and does not enter the overall Lumina composite.
Related
