Benchmark Almanac

MulSeT

Qwen2.5-VL-7B 36.7% leads since September 2025
Not in model cards

Models answer spatial questions about direction, distance and masks across views. The paper studies single images, multiple views and video.

The port lists Kimi, Gemini, Nemotron and Gemma runs. Gemma 3 27B reached mean reward 1.0 on one example on December 6, 2025.

Made by
Wanyue Zhang and colleagues
Released
September 2025
Kind
Spatial reasoning and counting
Level
University
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Images, Video → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
In views
Vision
Last model added
January 2025
Scores refreshed
November 20th, 2026
2
Models scored in its paper

Qwen2.5-VL-7B leads with 36.7%

Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best.

  1. 1 Qwen2.5-VL-7B Shuffle-LLM-txy 36.7%
  2. 2 LLaVA-OneVision 7B Vanilla 30.3%

Source: The MulSeT paper

#ModelScoreSettingDateSource
1 Qwen2.5-VL-7B 36.7% Shuffle-LLM-txy Jan 2025 Official leaderboard
2 LLaVA-OneVision 7B 30.3% Vanilla Aug 2024 Official leaderboard

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Qwen
Benchmark paper Not tested since Sep 2025

Source: The MulSeT paper

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) Qwen2.5-VL-7B LLaVA-OneVision 7B 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) Qwen2.5-VL-7B LLaVA-OneVision 7B

Source: Official MulSeT leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Vision

All 636 in Vision
  • MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. Qwen 3.6 Plus 86%
  • MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
  • CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
  • MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy. Seed2.1 Pro 90.7%
  • MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy. Qwen 3.8 Max 97.7%
  • MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy. Qwen 3.8 Max 85.9%

Data audit

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 22 months ago, in January 2025, for Qwen2.5-VL-7B. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (2 entries).
  • Note Models scored Only 2 models we track.
  • Warning Newest score The newest came 22 months ago, in January 2025, for Qwen2.5-VL-7B.
  • Note Frontier models None of its models are on the capabilities index.
  • Pass Headroom The best is 36.7%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 35 rows for models we track at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check