Compare AI models

Specifications
Parameters
5.1B/8B/26B/31B—
API pricing
Cheapest input
$0.04Darkbloom—
Cheapest output
$0.10Modal—
$14.70PrimeIntellect · bf16—
Benchmarks
MMLU-Pro
85.2%72%
Overview
CompanyGoogleSpaceXSI
Release dateApr 2 2026Aug 13 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Gemma 4 leads Grok‑2 mini on 1 of the 1 benchmark they both report (MMLU-Pro). Grok‑2 mini shipped 597 days before Gemma 4, so benchmark comparisons should account for the intervening progress.

Gemma 4 is open weight, while Grok‑2 mini is closed.

On MMLU-Pro, Gemma 4 leads at 85.2% vs Grok‑2 mini at 72%.