Benchmark Almanac

Qualcomm Interactive Cooking

MR-CAS 56.2% tops its leaderboard Gemini 2.5 Flash Sep 2025 23.1% leads the models we track
Not in model cards

Models watch a cook follow a recipe. They give timed instructions, recognize completed steps, and warn about mistakes. The benchmark scores completion accuracy and mistake detection.

The 2026 workshop used the main set of 109 test videos in turn-based mode. MR-CAS scored 56.2% instruction completion accuracy and 0.31 mistake F1.

Released
November 2025
Kind
Video understanding
Level
Everyday
Scored
Checked automatically
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Video, Text → Text
Interaction
Multi-turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
In views
Vision
Strongest model tested
Gemini 2.5 Flash Sep 2025 #112 on the capability index
Last model added
September 2025
Scores refreshed
November 20th, 2026
6
Entries on its own leaderboard, 3 models we track

MR-CAS tops the leaderboard with 56.2% Gemini 2.5 Flash leads with 23.1% among models released by September 2025

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Gemini 2.5 Flash, at 23.1%. This view shows only models we track, each at its best.

The newest model with a score here came out in September 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 MR-CAS 56.2%
  2. 2 Yeeun Choi 31.4%
  3. 3 Gemini 2.5 Flash Sep 2025 23.1%
  4. 4 Qwen2.5-VL-7B 18.9%
  5. 5 Qwen2-VL-7B-Instruct 6.30%
  6. 6 Videollm-online 0.03%

Source: Official Qualcomm Interactive Cooking leaderboard

Source: Official Qualcomm Interactive Cooking leaderboard

#EntryScoreSettingSubmitted byDateSource
1 MR-CAS 56.2% MR-CAS Official leaderboard
2 Yeeun Choi 31.4% Yeeun Choi Official leaderboard
3 Gemini 2.5 Flash Sep 2025 23.1% Sep 2025 Official leaderboard
4 Qwen2.5-VL-7B 18.9% Jan 2025 Official leaderboard
5 Qwen2-VL-7B-Instruct 6.30% Aug 2024 Official leaderboard
6 Videollm-online 0.03% Official leaderboard
#ModelScoreSettingSubmitted byDateSource
1 Gemini 2.5 Flash Sep 2025 23.1% Sep 2025 Official leaderboard
2 Qwen2.5-VL-7B 18.9% Jan 2025 Official leaderboard
3 Qwen2-VL-7B-Instruct 6.30% 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.

Google DeepMind
Own leaderboard Not tested since Nov 2025

Source: Official Qualcomm Interactive Cooking leaderboard

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
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) Gemini 2.5 Flash Qwen2.5-VL-7B Qwen2-VL-7B-Instruct 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) Gemini 2.5 Flash Qwen2-VL-7B-Instruct

Source: Official Qualcomm Interactive Cooking 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 Audio and video

All 695 in Audio and video
  • Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy. Qwen 3.8 Max 88.7%
  • LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization. Gemini 4 Argon 91.7%
  • MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy. Qwen 3.8 Max 82.4%
  • MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy. Qwen 3.8 Max 90.8%
  • FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better. Phi-4-multimodal 4.00%
  • VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules. Qwen3.5-Omni-Plus 93.1%

Data audit

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (6 entries).
  • Pass Models scored 3 models we track, plus 3 other entries on its leaderboard.
  • Warning Newest score The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 2.5 Flash (#112).
  • Pass Headroom The best is 23.1%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on varworkshop.github.io: 3 rows for models we track and 3 other entries 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