Gemini 3.6 FlashvsComposer 2.5

Gemini 3.6 Flash
Composer 2.5
Benchmarks
Nonsense detection
BullshitBench v2
39%
Prompt injection robustness
Gray Swan IPI · k = 1
7.3%
Prompt injection robustness
Gray Swan IPI · k = 10
32.2%
Prompt injection robustness
Gray Swan IPI · k = 15
37.3%
Agentic coding
SWE-Bench Pro
54%
Multilingual coding
SWE-Bench Multilingual
79.8%
Agentic coding
CursorBench v3.2
53.5%
56.1%Best
Agentic coding
CursorBench v3.1
63.2%
Agentic coding
DeepSWE 1.1
49%
Agentic coding
DeepSWE 1.0
18%
ML engineering
MLE-Bench
63.9%
Next.js coding
Next.js Evals
92%
Agentic terminal coding
Terminal-Bench 2.1
73%
Agentic terminal coding
Terminal-Bench 2.0
69.3%
Browser agent
BU Bench
68%
Agentic computer use
OSWorld-Verified
83%
Knowledge work
GDPval-AA v2
1421
Community preference
Arena Elo (Text)
1482
Community preference (code)
Arena Elo (Code)
1533
Overview
CompanyGoogleSpaceXAI
Release dateJul 21 2026May 18 2026
AccessProprietaryProprietary

Which is better: Gemini 3.6 Flash or Composer 2.5?

Composer 2.5 leads Gemini 3.6 Flash on 1 of the 1 benchmark they both report (CursorBench v3.2). Composer 2.5 shipped 64 days before Gemini 3.6 Flash, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On CursorBench v3.2, Composer 2.5 leads at 56.1% vs Gemini 3.6 Flash at 53.5%.

Frequently asked questions

Gemini 3.6 Flash was released by Google on Jul 21 2026.

Composer 2.5 was released by SpaceXAI on May 18 2026.

Composer 2.5 leads on CursorBench v3.2 — Gemini 3.6 Flash 53.5% vs Composer 2.5 56.1%.

Other comparisons