Skip to main content

Gemini 3.6 Flash on BlueBench

Gemini 3.6 Flash ranks 19th of 26 models on BlueBench, Cotool's benchmark for defensive security work, with an overall score of 62.7. It ranks highest in detection engineering (81.1, 7th of 26) and lowest in incident response (54.5, 21st of 26). It averages $3.01 per task, the 19th lowest cost of the 26 models tested.

Google · Closed weight · Updated Oct 2026
Methodology
BlueBench score
62.7
#19 of 26 models
Cost per task
$3.01
#19 cheapest of 26
Reliability
29.8
#19 of 26 models
Best-ranked track
#7
Detection Engineering · 81.1
Read the Gemini 3.6 Flash rundown →Verdict, strengths and weaknesses against similar-cost models, and when to pick something else.

Scores by track

BlueBench weights incident response, threat hunting, and detection engineering at 30% each and malware analysis at 10%.

TrackScoreRankTrack leader
Incident Response54.5#21 of 26GPT-6 Astra · 88.0
Threat Hunting53.0#18 of 26Claude Opus 5.5 · 76.1
Detection Engineering81.1#7 of 26GPT-6 Astra · 87.3
Malware Analysis61.6#23 of 26Claude Opus 5.5 · 89.4

Scores by benchmark

Each BlueBench benchmark is a separate intrusion, real or simulated, with its own tasks and grading.

Models ranked nearby

The models closest to Gemini 3.6 Flash on the overall leaderboard.

ModelRankScoreCost / task
#1765.5$1.03
#1864.1$0.26
Gemini 3.6 Flash
#1962.7$3.01
#2062.4$0.58
#2158.6$0.17

Frequently asked questions

How good is Gemini 3.6 Flash at security operations?
Gemini 3.6 Flash scores 62.7 overall on BlueBench and ranks 19th of 26 models on incident response, threat hunting, detection engineering, and malware analysis. The top model, Claude Opus 5.5, scores 83.2.
Which security tasks is Gemini 3.6 Flash best at?
BlueBench track scores for Gemini 3.6 Flash, best rank first. Detection Engineering: 81.1 (7th of 26); Threat Hunting: 53.0 (18th of 26); Incident Response: 54.5 (21st of 26); Malware Analysis: 61.6 (23rd of 26).
How much does Gemini 3.6 Flash cost per security task?
Gemini 3.6 Flash averages $3.01 per BlueBench task, including repeated attempts. That is the 19th lowest cost of 26 models. The best-scoring cheaper model is Claude Sonnet 5.5 at $1.01 per task with an overall score of 77.5.
How was Gemini 3.6 Flash tested?
Every model runs the same 74 tasks across 6 BlueBench benchmarks, built from real intrusion logs and simulated enterprise environments, using the same harness, prompts, tools, and number of trials. Reports are graded against hidden rubrics and detection rules are re-run against the evidence.

Full leaderboards

AI for the blue team.

Run Cotool's harness in your environment to get real security work done

Book a demo