Skip to main content

Gemini 3.1 Pro on BlueBench

Gemini 3.1 Pro ranks 25th of 26 models on BlueBench, Cotool's benchmark for defensive security work, with an overall score of 45.3. It ranks highest in threat hunting (43.2, 23rd of 26) and lowest in detection engineering (55.8, 26th of 26). It averages $4.63 per task, the 24th lowest cost of the 26 models tested.

Google · Closed weight · Updated Oct 2026
Methodology
BlueBench score
45.3
#25 of 26 models
Cost per task
$4.63
#24 cheapest of 26
Reliability
19.2
#23 of 26 models
Best-ranked track
#23
Threat Hunting · 43.2
Read the Gemini 3.1 Pro 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 Response32.6#25 of 26GPT-6 Astra · 88.0
Threat Hunting43.2#23 of 26Claude Opus 5.5 · 76.1
Detection Engineering55.8#26 of 26GPT-6 Astra · 87.3
Malware Analysis58.3#25 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 3.1 Pro on the overall leaderboard.

ModelRankScoreCost / task
#2256.4$0.90
#2353.6$0.91
#2450.5$4.44
Gemini 3.1 Pro
#2545.3$4.63
#2644.8$1.77

Frequently asked questions

How good is Gemini 3.1 Pro at security operations?
Gemini 3.1 Pro scores 45.3 overall on BlueBench and ranks 25th 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 3.1 Pro best at?
BlueBench track scores for Gemini 3.1 Pro, best rank first. Threat Hunting: 43.2 (23rd of 26); Malware Analysis: 58.3 (25th of 26); Incident Response: 32.6 (25th of 26); Detection Engineering: 55.8 (26th of 26).
How much does Gemini 3.1 Pro cost per security task?
Gemini 3.1 Pro averages $4.63 per BlueBench task, including repeated attempts. That is the 24th lowest cost of 26 models. The best-scoring cheaper model is Claude Opus 5.5 at $3.54 per task with an overall score of 83.2.
How was Gemini 3.1 Pro 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