# MathVista test

> MathVista tests mathematical reasoning about images. This table shows published accuracy on the test split, with each source configuration kept separate. The results are display only and do not enter overall or category rankings.

Canonical page: https://benchlm.ai/benchmarks/mathvista-test

- Category: [Multimodal & Grounded](/multimodal-grounded)
- Last updated: June 9, 2025

MathVista by [MathVista authors and website maintainers](https://mathvista.github.io/) and contributors. [Original benchmark](https://mathvista.github.io/) · [CC-BY-SA-4.0 license](https://creativecommons.org/licenses/by-sa/4.0/).

Selected aggregate-result compilation and its adaptation. Task content, source images, model outputs, and model weights are excluded. Selected aggregate scores and adjacent metadata; converted numeric strings to numbers and missing-score markers to null; separated testmini from test; added configuration notes and three named profile references.

This table contains 9 model or configuration records from the MathVista website compilation for test. The split has 5,141 examples; the aggregate files do not state a separate completed-example count for each record. The pinned source commit is dated June 9, 2025, and the source files were observed on October 15, 2026.

Each score belongs to the published configuration shown below it. Prompting, tools, image processing, and test-time compute can change the result. We keep the two splits separate and exclude these scores from overall and category rankings.

Reference baselines are outside the model table: Random Chance: 17.86%.

MathVista website compilation, CC BY-SA 4.0. Original result sources remain credited in each record. This adaptation retains CC BY-SA 4.0. Changes: Selected aggregate scores and adjacent metadata; converted numeric strings to numbers and missing-score markers to null; separated testmini from test; added configuration notes and three named profile references.

The compilation contains different evaluation setups; the highest reported value does not establish a comparable model ranking.

- [MathVista project and leaderboard](https://mathvista.github.io/)
- [Pinned MathVista result compilation](https://github.com/mathvista/mathvista.github.io/tree/a9daca33c6b3ae348b776e6586ec6b8a62656d29)
- [MathVista paper](https://arxiv.org/abs/2310.02255)
- [Website compilation license declaration](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/README.md)
- [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/)

## About MathVista test

- Year: 2023
- Tasks: 5,141 examples in the test split
- Format: Published accuracy (%)
- Difficulty: Mathematical reasoning in visual contexts
- Paper: [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://arxiv.org/abs/2310.02255)

The test split contains 5,141 examples. The pinned website compilation was committed on June 9, 2025 and observed on October 1, 2026. Source record counts describe published configurations, not distinct models or confirmed complete evaluation runs.

MathVista test is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (9 model or configuration records)

| Source configuration | Accuracy | Evaluation setup | Sources |
|---|---|---|---|
| [InternVL2-Pro](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/InternVL2-Pro/scores_test_internvl2_pro.json) | 65.84% | Published method: LMM 🖼️; Additional checkpoint and evaluation settings unverified; Source date 2024-09-04 (compiler field) | [Pinned aggregate](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/InternVL2-Pro/scores_test_internvl2_pro.json); [source metadata](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/InternVL2-Pro/meta.json); [original result](https://github.com/OpenGVLab/InternVL) |
| [InternVL-Chat-V1.2_Plus](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/InternVL-Chat-V1.2_Plus/scores_InternVL-Chat-V1.2-Plus.json) | 60.18% | Published method: LMM 🖼️; Additional checkpoint and evaluation settings unverified; Source date 2024-02-22 (compiler field) | [Pinned aggregate](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/InternVL-Chat-V1.2_Plus/scores_InternVL-Chat-V1.2-Plus.json); [source metadata](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/InternVL-Chat-V1.2_Plus/meta.json); [original result](https://arxiv.org/abs/2312.14238) |
| [InternLM-XComposer2-VL-7B](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/InternLM-XComposer2-VL-7B/scores_test_InternLM-XComposer2-VL.json) | 57.93% | Published method: LMM 🖼️; Additional checkpoint and evaluation settings unverified; Source date 2024-01-22 (compiler field) | [Pinned aggregate](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/InternLM-XComposer2-VL-7B/scores_test_InternLM-XComposer2-VL.json); [source metadata](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/InternLM-XComposer2-VL-7B/meta.json); [original result](https://github.com/InternLM/InternLM-XComposer) |
| [Qwen-VL-Plus](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/Qwen-VL-Plus/scores_test_qwenvl_plus_pretrain.json) | 44.33% | Published method: LMM 🖼️; Additional checkpoint and evaluation settings unverified; Source date 2023-12-21 (compiler field) | [Pinned aggregate](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/Qwen-VL-Plus/scores_test_qwenvl_plus_pretrain.json); [source metadata](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/Qwen-VL-Plus/meta.json); [original result](https://github.com/QwenLM/Qwen-VL) |
| [SPHINX-MoE](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/SPHINX-MoE/scores_mathvista_SPHINX-MoE_2E.json) | 42.68% | Published method: MoE 🤖; Additional checkpoint and evaluation settings unverified; Source date 2024-01-13 (compiler field) | [Pinned aggregate](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/SPHINX-MoE/scores_mathvista_SPHINX-MoE_2E.json); [source metadata](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/SPHINX-MoE/meta.json); [original result](https://github.com/Alpha-VLLM/LLaMA2-Accessory/tree/main/SPHINX) |
| [MiniCPM-V-2 (2.8B)](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/MiniCPM-V-2%20(2.8B)/scores_minicpm-v-2_test.json) | 39.89% | Published method: LMM 🖼️; Additional checkpoint and evaluation settings unverified; Source date 2024-04-14 (compiler field) | [Pinned aggregate](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/MiniCPM-V-2%20(2.8B)/scores_minicpm-v-2_test.json); [source metadata](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/MiniCPM-V-2%20(2.8B)/meta.json); [original result](https://github.com/OpenBMB/MiniCPM-V) |
| [PoT GPT-4 (Caption+OCR)](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/PoT%20GPT-4%20(Caption%2BOCR)/scores_test_gpt4_2shot_code_use_caption_ocr.json) | 31.74% | Caption and OCR inputs; published prompting setup; remaining tools and sampling settings unverified; Source date 2023-10-03 (compiler field) | [Pinned aggregate](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/PoT%20GPT-4%20(Caption%2BOCR)/scores_test_gpt4_2shot_code_use_caption_ocr.json); [source metadata](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/PoT%20GPT-4%20(Caption%2BOCR)/meta.json); [original result](https://arxiv.org/abs/2310.02255) |
| [CoT GPT4 (Caption+OCR)](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/CoT%20GPT4%20(Caption%2BOCR)/scores_test_gpt4_2shot_solution_use_caption_ocr.json) | 30.5% | Caption and OCR inputs; published prompting setup; remaining tools and sampling settings unverified; Source date 2023-10-03 (compiler field) | [Pinned aggregate](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/CoT%20GPT4%20(Caption%2BOCR)/scores_test_gpt4_2shot_solution_use_caption_ocr.json); [source metadata](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/CoT%20GPT4%20(Caption%2BOCR)/meta.json); [original result](https://arxiv.org/abs/2310.02255) |
| [LLaVA (LLaMA-2-13B)](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/LLaVA%20(LLaMA-2-13B)/scores_test_llava_llama_2_13b.json) | 25.4% | Published method: LMM 🖼️; Additional checkpoint and evaluation settings unverified; Source date 2023-10-03 (compiler field) | [Pinned aggregate](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/LLaVA%20(LLaMA-2-13B)/scores_test_llava_llama_2_13b.json); [source metadata](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/LLaVA%20(LLaMA-2-13B)/meta.json); [original result](https://arxiv.org/abs/2310.02255) |

Reference baselines, outside the model table: [Random Chance](https://raw.githubusercontent.com/mathvista/mathvista.github.io/a9daca33c6b3ae348b776e6586ec6b8a62656d29/data/results_test/Random%20Chance/scores_test_random_guess.json): 17.86%.

### Published task and skill scores

Missing values remain unreported. All values below are published accuracy percentages for the named source configuration.

- **InternVL2-Pro:** figure question answering: 65.02%; geometry problem solving: 64%; math word problem: 75.44%; textbook question answering: 72.4%; visual question answering: 52.27%; algebraic reasoning: 67.35%; arithmetic reasoning: 63.1%; geometry reasoning: 64.96%; logical reasoning: 30.41%; numeric commonsense: 44.54%; scientific reasoning: 66.98%; statistical reasoning: 72.47%.
- **InternVL-Chat-V1.2_Plus:** figure question answering: 52.18%; geometry problem solving: 56.17%; math word problem: 78.3%; textbook question answering: 61.62%; visual question answering: 55.53%; algebraic reasoning: 55.96%; arithmetic reasoning: 64.37%; geometry reasoning: 57.56%; logical reasoning: 21.65%; numeric commonsense: 46.08%; scientific reasoning: 60.04%; statistical reasoning: 60.1%.
- **InternLM-XComposer2-VL-7B:** figure question answering: 53.92%; geometry problem solving: 56.44%; math word problem: 77.12%; textbook question answering: 58.41%; visual question answering: 43.19%; algebraic reasoning: 54.81%; arithmetic reasoning: 57.64%; geometry reasoning: 57.98%; logical reasoning: 16.49%; numeric commonsense: 47.62%; scientific reasoning: 59.1%; statistical reasoning: 62.46%.
- **Qwen-VL-Plus:** figure question answering: 55.88%; geometry problem solving: 34.74%; math word problem: 29.68%; textbook question answering: 58.79%; visual question answering: 42.37%; algebraic reasoning: 40.7%; arithmetic reasoning: 35.4%; geometry reasoning: 36.64%; logical reasoning: 21.65%; numeric commonsense: 30.39%; scientific reasoning: 55.91%; statistical reasoning: 56.34%.
- **SPHINX-MoE:** figure question answering: 50.29%; geometry problem solving: 29.7%; math word problem: 40.93%; textbook question answering: 49.29%; visual question answering: 43.31%; algebraic reasoning: 33.88%; arithmetic reasoning: 43.05%; geometry reasoning: 29.08%; logical reasoning: 14.43%; numeric commonsense: 26.33%; scientific reasoning: 46.9%; statistical reasoning: 51.24%.
- **MiniCPM-V-2 (2.8B):** figure question answering: 51.74%; geometry problem solving: 27.45%; math word problem: 39.84%; textbook question answering: 42.49%; visual question answering: 34.69%; algebraic reasoning: 31.29%; arithmetic reasoning: 34.43%; geometry reasoning: 30.67%; logical reasoning: 13.4%; numeric commonsense: 33.47%; scientific reasoning: 38.46%; statistical reasoning: 50.03%.
- **PoT GPT-4 (Caption+OCR):** figure question answering: 27.58%; geometry problem solving: 37.35%; math word problem: 23.87%; textbook question answering: 43%; visual question answering: 30.27%; algebraic reasoning: 37.15%; arithmetic reasoning: 27.93%; geometry reasoning: 37.48%; logical reasoning: 22.68%; numeric commonsense: 15.83%; scientific reasoning: 44.47%; statistical reasoning: 31.87%.
- **CoT GPT4 (Caption+OCR):** figure question answering: 27.21%; geometry problem solving: 35.91%; math word problem: 21.3%; textbook question answering: 43.13%; visual question answering: 28.17%; algebraic reasoning: 35.72%; arithmetic reasoning: 25.17%; geometry reasoning: 35.8%; logical reasoning: 24.74%; numeric commonsense: 15.41%; scientific reasoning: 47.28%; statistical reasoning: 31.29%.
- **LLaVA (LLaMA-2-13B):** figure question answering: 22.86%; geometry problem solving: 24.57%; math word problem: 18.15%; textbook question answering: 35.82%; visual question answering: 29.69%; algebraic reasoning: 26.93%; arithmetic reasoning: 22.47%; geometry reasoning: 24.45%; logical reasoning: 19.07%; numeric commonsense: 19.05%; scientific reasoning: 34.71%; statistical reasoning: 21.61%.

## FAQ

### What does MathVista test measure?

MathVista tests mathematical reasoning about images. This table shows published accuracy on the test split, with each source configuration kept separate. The results are display only and do not enter overall or category rankings.

### Which source row has the highest reported MathVista test value?

InternVL2-Pro has the highest reported MathVista test value at 65.84%. The compilation contains different evaluation setups; the highest reported value does not establish a comparable model ranking.

### How many models are evaluated on MathVista test?

The June 9, 2025 contains 9 published model or configuration records.

### Does MathVista test affect BenchLM's overall score?

Not directly. MathVista test is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.