Skip to main content
Launching the open-source gateway

Gemini 2.5 Flash vs Gemma 4 31B

SpecGemini 2.5 FlashGemma 4 31B
Respan Index18.7 (#127)18.6 (#128)
Blended price per 1M$0.85-
Context window1.0M256K
Input / output per 1M$0.3 / $2.5$0 / $0
Max output66K-
Inputtext, vision, audiotext, vision
Released2025-06-172026-04-02

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.

CategoryGemini 2.5 FlashGemma 4 31B
Coding2.5 Gemini 2.5 Flash8.0 Gemma 4 31B
Agents18.5 Gemini 2.5 Flash12.7* Gemma 4 31B
Reasoning20.5 Gemini 2.5 Flash19.4 Gemma 4 31B
Knowledge & language13.6* Gemini 2.5 Flash10.8 Gemma 4 31B
Human preference46.7 Gemini 2.5 Flash50.0 Gemma 4 31B

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

Benchmarks both report

Gemma 4 31B leads on 5 of the 5 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkGemini 2.5 FlashGemma 4 31B
LMArena Elo14091452
LMArena Vision (LMArena)12161262
SAGE (Vals AI)44.8%55%
GPQA Diamond82.8%84.3%
Humanity's Last Exam (no tools)11%19.5%

FAQ

Is Gemini 2.5 Flash better than Gemma 4 31B?

Gemini 2.5 Flash scores 18.7 on the Respan Index (#127), ahead of Gemma 4 31B at 18.6 (#128). Gemma 4 31B leads on 5 of the 5 benchmarks both report.

Which has the larger context window?

Gemini 2.5 Flash accepts 1.0M tokens and Gemma 4 31B 256K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.