Skip to main content
Launching the open-source gateway

Gemini 4 Argon vs Gemma 4 31B

SpecGemini 4 ArgonGemma 4 31B
Respan Index69.1 (#8)18.6 (#128)
Blended price per 1M$2-
Context window-256K
Input / output per 1M$1 / $5$0 / $0
Max output1M-
Inputtext, vision, videotext, vision
Released2026-09-302026-04-02

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 4 ArgonGemma 4 31B
Coding55.9 Gemini 4 Argon8.0 Gemma 4 31B
Agents77.1 Gemini 4 Argon12.7* Gemma 4 31B
Reasoning78.1 Gemini 4 Argon19.4 Gemma 4 31B
Knowledge & language76.0 Gemini 4 Argon10.8 Gemma 4 31B
Human preference58.3 Gemini 4 Argon50.0 Gemma 4 31B

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

Benchmarks both report

Gemini 4 Argon leads on 7 of the 8 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkGemini 4 ArgonGemma 4 31B
SAGE 1.1 (Vals AI)89.5%82.8%
Chess Puzzles (Epoch AI)59%5%
GPQA Diamond96.4%84.3%
LMArena Elo15201452
LMArena WebDev (LMArena)16791369
OTIS Mock AIME 2024-2025 (Epoch AI)100%73.3%
SimpleQA Verified76%10.4%
SAGE (Vals AI)53.6%55%

FAQ

Is Gemini 4 Argon better than Gemma 4 31B?

Gemini 4 Argon scores 69.1 on the Respan Index (#8), ahead of Gemma 4 31B at 18.6 (#128). Gemini 4 Argon leads on 7 of the 8 benchmarks both report.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.