Mathematics

MathVista MINI

MathVista_MINI: mathematical reasoning with vision (mixed MCQ + free-form), binary correctness from VLMEval/OpenVLMRecords.

874items
263subjects
CC-BY-SA-4.0license
mathematicsdomain
textmodality
imagemodality
item-level responses released
Saturation status: Unknown

Response matrix

Fit to width. Hover for subject & item; click a cell for details.

MathVista MINI response matrix: AI models (rows) against items (columns)
Correct (1)Incorrect (0)Unobserved

Scale: 1 = correct · 0 = incorrect

Subjects

  1. 1InternVL2_5-38B0.568
  2. 2InternVL2_5-8B-MPO0.55
  3. 3InternVL2_5-26B0.525
  4. 4InternVL-Chat-V1-2-Plus0.52
  5. 5InternVL2-40B0.504
  6. 6InternVL2_5-38B-MPO0.502
  7. 7InternVL2_5-8B0.489
  8. 8InternVL2-8B-MPO0.485
  9. 9InternVL2-76B0.481
  10. 10InternVL2-26B0.481
  11. 11InternVL2_5-26B-MPO0.479
  12. 12InternVL2-4B0.474
  13. 13GPT4.50.471
  14. 14MMAlaya20.456
  15. 15Mini-InternVL-Chat-4B-V1-50.455
  16. 16GLM4V_PLUS0.45
  17. 17GLM4V_PLUS_202501110.441
  18. 18InternVL2_5-78B0.44
  19. 19InternVL-Chat-V1-50.439
  20. 20InternVL2_5-4B-MPO0.439
  21. 21InternVL2-8B0.429
  22. 22InternVL2_5-4B0.416
  23. 23GeminiPro2-00.416
  24. 24GPT4o_202408060.415
  25. 25QVQ-72B-Preview0.411
  26. 26InternVL2_5-78B-MPO0.409
  27. 27Step1.5V-mini0.403
  28. 28ChatGPT4o0.401
  29. 29InternVL2_5-2B-MPO0.396
  30. 30Qwen2.5-VL-7B-Instruct0.396
  31. 31Llama-3.2-90B-Vision-Instruct0.394
  32. 32GeminiPro2-50.394
  33. 33grok-2-vision-12120.393
  34. 34Claude3-5V_Sonnet_202410220.39
  35. 35GPT4o_HIGH0.39
  36. 36HunYuan-Standard-Vision0.389