priorsBuilder

Other · released 2025-02-26

Phi-4 Multimodal Instruct

Measured on 7 benchmarks.

General frontier

Not ranked in this mix — too little measured data for its benchmarks.

Your mix’s benchmarks

1 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #445none of 5875.0%

Leader: Opus 5.5 · 61.4%

All 7 benchmarks

show 6 more

coding

LiveCodeBench

282 results
  1. #243none of 28213.1%

Leader: Gemini 3 Pro · 91.7%

composite

AA Intelligence Index v4.3.2

610 results
  1. #532none of 6105.8

Leader: Opus 5.5 · 57.6

knowledge

GPQA Diamond

539 results
  1. #497none of 53931.5%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #244none of 28548.5%

Leader: Gemini 3 Pro · 89.8%

knowledge

MMMU-Pro

265 results
  1. #265none of 26514.5%

Leader: Opus 5.5 · 87.7%

math

MATH-500

162 results
  1. #119none of 16269.3%

Leader: GPT-5 · 99.4%