Project AURIONAI Use-Cases Research & Innovation

AI2D

multimodal.

multimodal

Score in %, Claude 3 model card, Table 1 and vision table

  1. 1AnthropicClaude 3 Sonnet88.7 %vendor-reported
  2. 2AnthropicClaude 3 Opus88.1 %vendor-reported
4scores
4models
0independent
0maintainer-run
4vendor-reported

Definition

Version
not in the notes
Category
multimodal
Maintainer
not in the notes
Status
not in the notes
Home page
not in the notes

Sources

  1. huggingface.co/microsoft/Phi-4-reasoning-vision-15B https://huggingface.co/microsoft/Phi-4-reasoning-vision-15B

Scores at a Glance

Score in %, Claude 3 model card, Table 1 and vision table

Higher is better for this unit.

1AnthropicClaude 3 SonnetAnthropictest set
88.7 %
vendor-reported2AnthropicClaude 3 OpusAnthropictest set
88.1 %
vendor-reported
0255075100
Where this comes from
Each bar is one model, with its most independent recorded score. Hatched bars are vendor-reported; the word beside each bar says who ran it. Settings and dates differ between rows; the Scores table below has every result.

Scores

4 of 4 scores shown ai2d-scores.csv
ModelScoreWho ran itSettingView or populationDateSource
Mistral AIPixtral Large93.8 %vendor-reportedBBoxPixtral Large model card18 Nov 2024huggingface.co
AnthropicClaude 3 Sonnet88.7 %vendor-reportedtest setClaude 3 model card, Table 1 and vision tableMar 2024www-cdn.anthropic.com
AnthropicClaude 3 Opus88.1 %vendor-reportedtest setClaude 3 model card, Table 1 and vision tableMar 2024www-cdn.anthropic.com
Microsoft AIPhi-4-reasoning-vision-15B84.8 %vendor-reported–––huggingface.co
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "AI2D", https://aurion.semai.id/benchmarks/ai2d/, records of October 2026.