Skip to main content

Gemma 4 31B vs GPT-5 nano

SpecGemma 4 31BGPT-5 nano
Respan Index18.7 (#139)18.8 (#137)
Blended price per 1M-$0.138
Context window256K400K
Input / output per 1M$0 / $0$0.05 / $0.4
Max output-128K
Inputtext, visiontext, vision
Released2026-04-022025-08-07

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 31BGPT-5 nano
Coding7.8 Gemma 4 31B4.2 GPT-5 nano
Agents12.5* Gemma 4 31B18.5* GPT-5 nano
Reasoning19.7 Gemma 4 31B25.3 GPT-5 nano
Knowledge & language11.0 Gemma 4 31B11.7 GPT-5 nano
Human preference50.5 Gemma 4 31B37.6 GPT-5 nano

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

Benchmarks both report

Gemma 4 31B leads on 5 of the 8 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkGemma 4 31BGPT-5 nano
LMArena Elo14521338
LMArena Vision (LMArena)12651148
Chess Puzzles (Epoch AI)5%22%
GPQA Diamond84.3%69.4%
OTIS Mock AIME 2024-2025 (Epoch AI)73.3%81.1%
SAGE (Vals AI)55%30.4%
SimpleQA Verified10.4%11.7%
WeirdML (Håvard Tveit Ihle)52.3%38.1%

FAQ

Is Gemma 4 31B better than GPT-5 nano?

GPT-5 nano scores 18.8 on the Respan Index (#137), ahead of Gemma 4 31B at 18.7 (#139). Gemma 4 31B leads on 5 of the 8 benchmarks both report.

Which has the larger context window?

Gemma 4 31B accepts 256K tokens and GPT-5 nano 400K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.