Multimodal benchmark

# ScienceQA leaderboard

> ScienceQA results for 6 AI models, led by GPT-4o at 88.5%. What the benchmark measures, who runs it, and a source for every score.
- Canonical page: https://noometry.com/benchmarks/scienceqa
- Last updated: 2026-10-10
- Title: ScienceQA Leaderboard (October 2026): Scores by Model

As of October 2026, GPT-4o has the highest published ScienceQA score on Noometry at 88.5%, out of 6 models with results.

Last verified October 10, 2026

## About ScienceQA

Multimodal grade-school science questions with image and text context.

- **Category:** [Multimodal](https://noometry.com/best/multimodal)
- **Introduced:** 2022
- **Format:** Multiple choice
- **Unit:** Percent (random guessing ≈ 25%)
- **Official site:** [scienceqa.github.io](https://scienceqa.github.io)

## Top 6 models

Top models on ScienceQA

1.  GPT-4o 88.5%
2.  Gemini 1.0 Pro Vision 79.7%
3.  Claude 3 Haiku 72%
4.  Llama 2-13B 55.8%
5.  Llama 13b 43.3%
6.  Llama 2-7B 43.1%
7.  050100

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## All results

ScienceQA results by model
| # | Model | Provider | Score | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- | --- |
| 1 | [GPT-4o](https://noometry.com/models/gpt-4o) | [OpenAI](https://noometry.com/providers/openai) | 88.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 2 | [Gemini 1.0 Pro Vision](https://noometry.com/models/gemini-1-0-pro-vision) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 79.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 3 | [Claude 3 Haiku](https://noometry.com/models/claude-3-haiku) | [Anthropic](https://noometry.com/providers/anthropic) | 72% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 4 | [Llama 2-13B](https://noometry.com/models/llama-2-13b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 55.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 5 | [Llama 13b](https://noometry.com/models/llama-13b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 43.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 6 | [Llama 2-7B](https://noometry.com/models/llama-2-7b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 43.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

## Compare the leaders

-   [GPT-4o vs Gemini 1.0 Pro Vision](https://noometry.com/compare/gemini-1-0-pro-vision-vs-gpt-4o)
-   [GPT-4o vs Claude 3 Haiku](https://noometry.com/compare/claude-3-haiku-vs-gpt-4o)
-   [GPT-4o vs Llama 2-13B](https://noometry.com/compare/gpt-4o-vs-llama-2-13b)
-   [GPT-4o vs Llama 13b](https://noometry.com/compare/gpt-4o-vs-llama-13b)
-   [Gemini 1.0 Pro Vision vs Claude 3 Haiku](https://noometry.com/compare/claude-3-haiku-vs-gemini-1-0-pro-vision)
-   [Gemini 1.0 Pro Vision vs Llama 2-13B](https://noometry.com/compare/gemini-1-0-pro-vision-vs-llama-2-13b)

## Other multimodal benchmarks

-   [LMArena Vision](https://noometry.com/benchmarks/arena-vision)
-   [Video-MME](https://noometry.com/benchmarks/video-mme)
-   [GeoBench](https://noometry.com/benchmarks/geobench)
-   [VPCT](https://noometry.com/benchmarks/vpct)
-   [Blueprint-Bench 2](https://noometry.com/benchmarks/blueprint-bench-2)
-   [Furniture Assembly](https://noometry.com/benchmarks/furniture-assembly)
-   [LMArena Document](https://noometry.com/benchmarks/arena-document) (reference)
-   [MindCube](https://noometry.com/benchmarks/mindcube) (reference)
-   [SpatialViz-Bench](https://noometry.com/benchmarks/spatialviz-bench) (reference)

## Frequently asked questions

### What does ScienceQA measure?

Multimodal grade-school science questions with image and text context.

### Which model has the highest ScienceQA score?

As of October 2026, GPT-4o has the highest published ScienceQA score on Noometry at 88.5%, out of 6 models with results.

### What is the best open-weight model on ScienceQA?

Llama 2-13B has the highest ScienceQA accuracy among open-weight models at 55.8%, ranking 4 of 6 overall.

### Cite this page

Noometry. (2026). ScienceQA leaderboard. Retrieved October 10, 2026, from https://noometry.com/benchmarks/scienceqa

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/benchmarks/scienceqa.md).