Artificial Analysis · Intelligence Index · ReasoningBenchmarks, as Artificial Analysis ran them- 79%GPQA Diamond
- 19%Humanity's Last Exam
- 39%Terminal-Bench 2.1
- 14%Terminal-Bench Hard
- 40%SciCode
- 44%τ²-Bench
- 12%τ²-Bench Banking
- 72%IFBench
- 66%Long context reasoning
- Speed
- 80.6 tokens/s
- First answer
- 0.7 s
- thinking included
- Per 1M tokens
- $0.10 in · $0.34 out
- Context
- 262K tokens
LMArena · Text101stof 417· 24th of 227 open models
Against list priceRating for the price
Gemma 4 26B A4B · 1,438 · $0.14 per 1M tokens ($0.09 in, $0.30 out) · 262K context
Gemma 4 26B A4B · 1,438 · $0.14 per 1M tokens ($0.09 in, $0.30 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