1. Models
  2. Google
  3. CWE-Bench Gemini Pass@1 vs. Cost per Rollout
GoogleBlog · Sep 2, 2026 · official

CWE-Bench Gemini Pass@1 vs. Cost per Rollout

Gemini 3.8 Flash Cyber leads Pareto frontier in accuracy vs cost

BlogScatter plotGemini 3All Google modelsGLM-5.3Deepseek V4 FlashKimi K3Fable 5Gemini 3.8 Flash CyberGPT 5.6 SolOpus 4.8Gemini 3.7 Flash
Published by Google on Blog, Sep 2, 2026. Source: deepmind.google

API

Not in the API yet

We have not read this chart's numbers yet, so the API has nothing to return for it. Charts with numbers read are on the data page, and each one can be called by id.

Charts with dataAPI docs

More charts about Gemini 3

Gemini 3: Codeforces Coding and Algorithms
OfficialX · GoogleFeb 12, 2026
Codeforces Coding and Algorithms695.4K views · 1.9K likes
Data
Gemini 3: Gemini 3 Deep Think on Humanity's Last Exam
OfficialX · GoogleFeb 12, 2026
Gemini 3 Deep Think on Humanity's Last Exam695.4K views · 1.9K likes
Data
Gemini 3: MMMU-Pro Multimodal Understanding and Reasoning
OfficialX · GoogleFeb 12, 2026
MMMU-Pro Multimodal Understanding and Reasoning695.4K views · 1.9K likes
Data
Gemini 3: ARC-AGI-2 Reasoning & Knowledge
OfficialX · GoogleFeb 12, 2026
ARC-AGI-2 Reasoning & Knowledge695.4K views · 1.9K likes
Data
Gemini 3: Gemini 3.7 Flash Enterprise automation workflow
OfficialX · GoogleAug 13, 2026
Gemini 3.7 Flash Enterprise automation workflow205.1K views · 581 likes
Data
Gemini 3: Long-horizon software engineering performance
OfficialX · GoogleAug 13, 2026
Long-horizon software engineering performance205.1K views · 581 likes
Data

More from Google

Google table chart: Gemini 4 Argon benchmark comparison5.7x
Google·Sep 2026
Gemini 4 Argon benchmark comparison
3.9M views25.9K likes0.8% eng.
Data
Google annotated chart: Alphabet Q2 metrics2.8x
Google·Jul 2026
Alphabet Q2 metrics
3.9M views12.6K likes0.4% eng.
Data
Google annotated chart: Just posted Q3 earnings. We delivered our first-ever3.2x
Google·Oct 2025
Just posted Q3 earnings. We delivered our first-ever
2.9M views14.6K likes0.6% eng.
Data
Gemini 4: AI Model Benchmark Comparison
OfficialX · GoogleSep 30, 2026
AI Model Benchmark Comparison9M views · 43K likes
Data
Gemma 4: Model Performance vs Size
OfficialX · GoogleApr 9, 2026
Model Performance vs Size886.1K views · 1.7K likes
Data
Gemini 2: Gemini 2.5 Flash Native Audio Benchmarks
OfficialX · GoogleDec 16, 2025
Gemini 2.5 Flash Native Audio Benchmarks212.3K views · 1.7K likes
Data
Gemini 2: Gemini 3 Deep Think Benchmark Performance
OfficialX · GoogleDec 4, 2025
Gemini 3 Deep Think Benchmark Performance188.8K views · 457 likes
Data
Gemma specialist models: Model Benchmark Comparison
OfficialX · GoogleFeb 21, 2024
Model Benchmark Comparison147.2K views · 335 likes
Data
Gemini 2: WebDev Arena Leaderboard
OfficialX · GoogleMay 6, 2025
WebDev Arena Leaderboard92.5K views · 448 likes
Data

Questions people ask

Where does this chart come from?

Google published it on Sep 2, 2026 on Blog (deepmind.google). We keep it here, with the publisher and date credited as text, so you can study it without leaving.

Can I make a chart like this?

Use the format, not the picture. The maker on any chart page redraws this type with your own numbers and words.