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: No

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_5-38B0.5865
  2. 2InternVL2_5-8B-MPO0.5656
  3. 3InternVL2_5-26B0.5427
  4. 4InternVL-Chat-V1-2-Plus0.5365
  5. 5InternVL2-40B0.5198
  6. 6InternVL2_5-38B-MPO0.5177
  7. 7InternVL2_5-8B0.5021
  8. 8InternVL2-8B-MPO0.501
  9. 9InternVL2-26B0.499
  10. 10InternVL2-76B0.4958
  11. 11InternVL2_5-26B-MPO0.4927
  12. 12InternVL2-4B0.4896
  13. 13GPT4.50.4854
  14. 14MMAlaya20.474
  15. 15Mini-InternVL-Chat-4B-V1-50.4729
  16. 16GLM4V_PLUS0.4635
  17. 17GLM4V_PLUS_202501110.4594
  18. 18InternVL-Chat-V1-50.4552
  19. 19InternVL2_5-4B-MPO0.4552
  20. 20InternVL2_5-78B0.45
  21. 21InternVL2-8B0.4448
  22. 22GeminiPro2-00.4333
  23. 23GPT4o_202408060.4323
  24. 24QVQ-72B-Preview0.4281
  25. 25InternVL2_5-4B0.4281
  26. 26InternVL2_5-78B-MPO0.4219
  27. 27Step1.5V-mini0.4188
  28. 28ChatGPT4o0.4146
  29. 29Qwen2.5-VL-7B-Instruct0.4104
  30. 30GeminiPro2-50.4094
  31. 31Llama-3.2-90B-Vision-Instruct0.4094
  32. 32InternVL2_5-2B-MPO0.4083
  33. 33grok-2-vision-12120.4073
  34. 34GPT4o_HIGH0.4062
  35. 35HunYuan-Standard-Vision0.4042
  36. 36Claude3-5V_Sonnet_202410220.4042