Benchmark Almanac

OmniLabel

DesCo 29.8% tops its leaderboard
Not in model cards

Models locate objects described by category names and free-form phrases. The benchmark compares predicted boxes with annotated objects.

Made by
OmniLabel team
Released
April 2023
Kind
Detection and captioning
Level
Everyday
Scored
Checked automatically
Answers
Prediction
Tasks
All public
Measures
Capability
Language
English
In and out
Images, Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
In views
Vision
18
Entries on its own leaderboard, 0 models we track

DesCo tops the leaderboard with 29.8%

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.

  1. 1 DesCo Track A 29.8%
  2. 2 TXT Track A 26.5%
  3. 3 sanghyeokchu Track C 26.4%
  4. 4 USTCxNetEaseFuxi Track C 24.7%
  5. 5 Fivewin Track A 24.6%
  6. 6 twangnh Track A 18.3%
  7. 7 GLIP-T-baseline-OmniLabel-Team Track A 18.3%
  8. 8 Test-team-setting Track B 18.3%
  9. 9 THU_team Track A 18.3%
  10. 10 kangsul Track A 18%
  11. 11 Turbo Track A 10%
  12. 12 奥迪-top_car Track A 10%
  13. 13 warriors_ Track C 6.34%
  14. 14 chenyuming Track A 3.44%
  15. 15 tobesixty Track A 2.91%
  16. 16 schoi Track A 0.04%
  17. 17 Bhathiya Track A 0.01%
  18. 18 KatsukiOHTO Track A 0%

Source: Official OmniLabel leaderboard

#EntryScoreSettingSubmitted byDateSource
1 DesCo 29.8% Track A, DesCo l_harold May 2023 Official leaderboard
2 TXT 26.5% Track A, TXT tuyentx May 2023 Official leaderboard
3 sanghyeokchu 26.4% Track C, sanghyeokchu sanghyeokchu May 2023 Official leaderboard
4 USTCxNetEaseFuxi 24.7% Track C, USTCxNetEaseFuxi USTCxNetEaseFuxi May 2023 Official leaderboard
5 Fivewin 24.6% Track A, Fivewin abcaaa May 2023 Official leaderboard
6 twangnh 18.3% Track A, twangnh twangnh May 2023 Official leaderboard
7 GLIP-T-baseline-OmniLabel-Team 18.3% Track A, GLIP-T-baseline-OmniLabel-Team xiaofeng94 May 2023 Official leaderboard
8 Test-team-setting 18.3% Track B, Test-team-setting yumin May 2023 Official leaderboard
9 THU_team 18.3% Track A, THU_team THU_team May 2023 Official leaderboard
10 kangsul 18% Track A, kangsul kangsul May 2023 Official leaderboard
11 Turbo 10% Track A, Turbo Turbo May 2023 Official leaderboard
12 奥迪-top_car 10% Track A, 奥迪-top_car audi666 May 2023 Official leaderboard
13 warriors_ 6.34% Track C, warriors_ warriors_ May 2023 Official leaderboard
14 chenyuming 3.44% Track A, chenyuming chenyuming Jan 2024 Official leaderboard
15 tobesixty 2.91% Track A, tobesixty tobesixty May 2023 Official leaderboard
16 schoi 0.04% Track A, schoi schoi May 2023 Official leaderboard
17 Bhathiya 0.01% Track A, Bhathiya Bhathiya Jun 2024 Official leaderboard
18 KatsukiOHTO 0% Track A, KatsukiOHTO katsuki.ohto May 2023 Official 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

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (18 entries).
  • Pass Models scored 18 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom No scores yet.
Leaderboard import 3 pass
  • Pass Importer We read the board on omnilabel.org: 18 entries at the last read, none a model we track.
  • 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