COCO Captions
Gemma 3 27B 116.0 leads since Mar 2025 Dropped Models write a caption for each image, and outputs are compared with five human captions per image using BLEU, METEOR, ROUGE, and CIDEr.
Model cards usually report CIDEr, which is not a percentage.
In the authors’ words
In this paper we describe the Microsoft COCO Caption dataset and evaluation server. When completed, the dataset will contain over one and a half million captions describing over 330,000 images. For the training and validation images, five independent human generated captions will be provided. To ensure consistency in evaluation of automatic caption generation algorithms, an evaluation server is used. The evaluation server receives candidate captions and scores them using several popular metrics, including BLEU, METEOR, ROUGE and CIDEr. Instructions for using the evaluation server are provided.
- Level
- Everyday Most adults, without training
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
Gemma 3 27B leads with 116.0 among models released by Mar 2025
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in Mar 2025, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 1 Gemma 3 27B 116.0
- 2 Gemma 3 12B 111.0
- 3 Gemma 3 4B 102.0
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Gemma 3 27B | 116.0 | Mar 2025 | Model card | |
| 2 | Gemma 3 12B | 111.0 | Mar 2025 | Model card | |
| 3 | Gemma 3 4B | 102.0 | Mar 2025 | Model card |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No launch post has listed it since Mar 2025
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 12 Mar 2025 | Gemma 3 27B | 116 | COCOcap (PT) |
3 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 25 Mar 2025 | Gemma 3 4B technical report | 102 | COCO caption, CIDEr, PT, 4-shot, val split without P&S (Table 11) | Capabilities |
| 25 Mar 2025 | Gemma 3 27B technical report | 116 | COCO caption, CIDEr, PT, 4-shot, val split without P&S (Table 11) | Capabilities |
| 25 Mar 2025 | Gemma 3 12B technical report | 111 | COCO caption, CIDEr, PT, 4-shot, val split without P&S (Table 11) | Capabilities |
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. GPT-5.1 85.4%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. Kimi K3.1 Pro 84.1%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy.
Qwen 3.8 Max 97.7% - ChartQA In use Models answer human-written and generated questions about chart images that need visual and arithmetic reasoning. Scored by relaxed accuracy with a 5 percent numeric tolerance.
Command A Vision 90.9% - DocVQA In use Models answer 50,000 questions about 12,000 scanned document images by reading their text and layout. Scoring is ANLS, a string similarity to reference answers.
Seed1.5-VL 96.9%