Artificial Analysis · Intelligence Index · ReasoningBenchmarks, as Artificial Analysis ran them- 86%GPQA Diamond
- 24%Humanity's Last Exam
- 0%Terminal-Bench 4.0
- 43%Terminal-Bench 2.1
- 36%Terminal-Bench Hard
- 46%SciCode
- 60%τ²-Bench
- 15%τ²-Bench Banking
- 76%IFBench
- 70%Long context reasoning
- Speed
- 35.1 tokens/s
- First answer
- 0.9 s
- thinking included
- Context
- 262K tokens
LMArena · Text76thof 417· 15th of 227 open models
Against list priceRating for the price
Gemma 4 31B · 1,452 · $0.25 per 1M tokens ($0.20 in, $0.40 out) · 262K context
Gemma 4 31B · 1,452 · $0.25 per 1M tokens ($0.20 in, $0.40 out) · 262K context
LMArena, CC BY 4.0, 15 October 2026 · prices OpenRouter, list price blended 3:1, read 22 October 2026 · Artificial Analysis, read 22 October 2026
Gemma 4 31B