nocaps
Models caption photographs that contain objects outside the caption training vocabulary. The benchmark compares generated captions with human references.
- Made by
- Harsh Agrawal and colleagues
- Released
- December 2018
- Kind
- Detection and captioning
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision
GIT2 tops the leaderboard with 124.8
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 GIT2 Single Model 124.8
- 2 PaLI Single Model 124.4
- 3 GIT Single Model 123.4
- 4 CoCa 120.5
- 5 EVCap 116.8
- 6 Prismer 110.8
- 7 phi 1.5 448 every 2 110.7
- 8 SimVLM Single Model 110.3
- 9 phi 1.5 448 every 2 more vqa 110.0
- 10 phi 1.5 672 every 2 stvqa 106.7
- 11 VinVL 92.5
- 12 ViTCAP CIDEr-136.7-ENC-DEC-ViTbfocal10-test-CBS 87.6
- 13 RCAL 82.9
- 14 Oscar 80.9
- 15 camel XE 75.9
- 16 UpDown ELMo + CBS 73.1
- 17 Neural Baby Talk CBS 61.5
- 18 IVLT t1-02-FT 52.6
Source: Official nocaps leaderboard
| # | Entry | Score | Setting | Submitted by | Date | Source |
|---|---|---|---|---|---|---|
| 1 | GIT2 | 124.8 | Single Model | MS. Cog. Svcs. | Aug 2022 | Official leaderboard |
| 2 | PaLI | 124.4 | Single Model | PaLI - Google Research | Sep 2022 | Official leaderboard |
| 3 | GIT | 123.4 | Single Model | MS Cog. Svcs. | May 2022 | Official leaderboard |
| 4 | CoCa | 120.5 | CoCa - Google Brain | Apr 2022 | Official leaderboard | |
| 5 | EVCap | 116.8 | EVCap | Nov 2023 | Official leaderboard | |
| 6 | Prismer | 110.8 | Prismer - Nvidia | Jan 2023 | Official leaderboard | |
| 7 | phi 1.5 448 every 2 | 110.7 | pheye | Apr 2024 | Official leaderboard | |
| 8 | SimVLM | 110.3 | Single Model | SimVLM - Google Brain | Jul 2021 | Official leaderboard |
| 9 | phi 1.5 448 every 2 more vqa | 110.0 | sdfageqbqeb | Apr 2024 | Official leaderboard | |
| 10 | phi 1.5 672 every 2 stvqa | 106.7 | blablablaasafafas | Apr 2024 | Official leaderboard | |
| 11 | VinVL | 92.5 | VinVL (Microsoft Cognitive Services + MSR) | Nov 2020 | Official leaderboard | |
| 12 | ViTCAP | 87.6 | CIDEr-136.7-ENC-DEC-ViTbfocal10-test-CBS | One-stage Captioner | Oct 2021 | Official leaderboard |
| 13 | RCAL | 82.9 | anonymous1234 | May 2020 | Official leaderboard | |
| 14 | Oscar | 80.9 | hellocaption | Apr 2020 | Official leaderboard | |
| 15 | camel | 75.9 | XE | copencop | Aug 2022 | Official leaderboard |
| 16 | UpDown | 73.1 | ELMo + CBS | nocaps Team | May 2019 | Official leaderboard |
| 17 | Neural Baby Talk | 61.5 | CBS | nocaps Team | May 2019 | Official leaderboard |
| 18 | IVLT | 52.6 | t1-02-FT | luo | Dec 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
- 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 Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on nocaps.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.