Gemini 3.6 FlashvsComposer 2.5
Gemini 3.6 Flash | Composer 2.5 | |
|---|---|---|
| Benchmarks | ||
Nonsense detection BullshitBench v2Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 39% | — |
Prompt injection robustness Gray Swan IPI · k = 1Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. Gray Swan's indirect prompt injection benchmark measures how often such an attack succeeds when the attacker gets a single try. Lower is better. | 7.3% | — |
Prompt injection robustness Gray Swan IPI · k = 10Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 10 tries and counts an attack as successful if any of them works. Lower is better. | 32.2% | — |
Prompt injection robustness Gray Swan IPI · k = 15Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 15 tries and counts an attack as successful if any of them works. Lower is better. | 37.3% | — |
Agentic coding SWE-Bench ProCan the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | — | 54% |
Multilingual coding SWE-Bench MultilingualLike SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | — | 79.8% |
Agentic coding CursorBench v3.2Cursor's own test of harder, real-world coding tasks inside a code editor, on the refreshed v3.2 task set. Scores aren't comparable with v3.1. Higher is better. | 53.5% | 56.1%Best |
Agentic coding CursorBench v3.1Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better. | — | 63.2% |
Agentic coding DeepSWE 1.1Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | 49% | — |
Agentic coding DeepSWE 1.0Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. Higher is better. | — | 18% |
ML engineering MLE-BenchCan the AI do the work of a machine-learning engineer? It competes in real Kaggle competitions — building, training, and tuning models end to end — and the score reflects how well it places. Higher is better. | 63.9% | — |
Next.js coding Next.js EvalsVercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | — | 92% |
Agentic terminal coding Terminal-Bench 2.1Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | — | 73% |
Agentic terminal coding Terminal-Bench 2.0Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | — | 69.3% |
Browser agent BU BenchCan the AI drive a real web browser to finish tasks — clicking, filling forms, and navigating sites the way a person would? Run by Browser Use on their BU Bench task set. Higher is better. | 68% | — |
Agentic computer use OSWorld-VerifiedCan the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 83% | — |
Knowledge work GDPval-AA v2economically valuable knowledge work (v2, re-based Elo) | 1421 | — |
Community preference Arena Elo (Text)Real people chat with two anonymous AIs side by side and vote for the answer they prefer. Votes become a chess-style Elo rating on arena.ai — it measures which AI people actually like, not test scores. Higher is better. | 1482 | — |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | 1533 | — |
| Overview | ||
| Company | SpaceXAI | |
| Release date | Jul 21 2026 | May 18 2026 |
| Access | Proprietary | Proprietary |
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
Gemini 3.6 FlashvsClaude Opus 5Composer 2.5vsClaude Opus 5Gemini 3.6 FlashvsGPT-5.6-CyberComposer 2.5vsGPT-5.6-CyberGemini 3.6 FlashvsMuse GlimmerComposer 2.5vsMuse GlimmerGemini 3.6 FlashvsDeepSeek-V4-Pro-0813Composer 2.5vsDeepSeek-V4-Pro-0813Gemini 3.6 FlashvsMistral Medium 3.5Composer 2.5vsMistral Medium 3.5Gemini 3.6 FlashvsKimi K3Composer 2.5vsKimi K3