priorsBuilder

Google · released 2026-04-02

Gemma 4 31B IT

Measured on 6 benchmarks.

General frontier

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

Your mix’s benchmarks

1 of 8 measured

reasoning

BullshitBench v2

196 results
  1. #134high of 19625.0%
  2. #146none of 19620.0%

Leader: Opus 4.8 · 95.0%

All 6 benchmarks

show 5 more

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #34high of 6339.3%

Leader: GPT-5.5 · 73.2%

coding

WeirdML v2

127 results
  1. #60high of 12752.3%

Leader: GPT-6 Astra Pro · 93.6%

economics

MortgageTax (Vals)

84 results
  1. #56high of 8461.4%

Leader: Opus 5 · 72.1%

knowledge

CaseLaw (Vals)

53 results
  1. #43high of 5352.6%

Leader: Grok 4.3 · 79.3%

reasoning

SAGE

80 results
  1. #2high of 8055.0%

Leader: Opus 4.7 · 56.1%