Skip to main content
Launching the open-source gateway

Gemma 4 26B A4B vs o3-mini

SpecGemma 4 26B A4Bo3-mini
Respan Index18.4 (#132)17.8 (#134)
Blended price per 1M-$1.93
Context window256K200K
Input / output per 1M$0 / $0$1.1 / $4.4
Max output-100K
Inputtext, visiontext
Released2026-04-022025-01-31

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryGemma 4 26B A4Bo3-mini
Coding4.4 Gemma 4 26B A4B4.6 o3-mini
Agents13.6* Gemma 4 26B A4B14.1* o3-mini
Reasoning20.1 Gemma 4 26B A4B22.4 o3-mini
Knowledge & language14.0 Gemma 4 26B A4B15.3 o3-mini
Human preference49.6 Gemma 4 26B A4B40.3 o3-mini

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

Gemma 4 26B A4B leads on 3 of the 5 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkGemma 4 26B A4Bo3-mini
LMArena Elo14381364
Chess Puzzles (Epoch AI)6%15%
GPQA Diamond82.3%74.9%
OTIS Mock AIME 2024-2025 (Epoch AI)82.2%76.9%
WeirdML (Håvard Tveit Ihle)35.2%43.7%

FAQ

Is Gemma 4 26B A4B better than o3-mini?

Gemma 4 26B A4B scores 18.4 on the Respan Index (#132), ahead of o3-mini at 17.8 (#134). Gemma 4 26B A4B leads on 3 of the 5 benchmarks both report.

Which has the larger context window?

Gemma 4 26B A4B accepts 256K tokens and o3-mini 200K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.