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
Scores by track
BlueBench weights incident response, threat hunting, and detection engineering at 30% each and malware analysis at 10%.
| Track | Score | Rank | Track leader |
|---|---|---|---|
| Incident Response | 32.6 | #25 of 26 | GPT-6 Astra · 88.0 |
| Threat Hunting | 43.2 | #23 of 26 | Claude Opus 5.5 · 76.1 |
| Detection Engineering | 55.8 | #26 of 26 | GPT-6 Astra · 87.3 |
| Malware Analysis | 58.3 | #25 of 26 | Claude Opus 5.5 · 89.4 |
Scores by benchmark
Each BlueBench benchmark is a separate intrusion, real or simulated, with its own tasks and grading.
| Benchmark | Score | Rank |
|---|---|---|
| Simulation-003Impact & Exfiltration | 40.6 | #26 of 26 |
| Simulation-002Identity & Active Directory Attacks | 40.7 | #25 of 26 |
| Simulation-001Initial Access & Command-and-Control | 29.9 | #25 of 26 |
| Intrusion-003AWS Cloud Intrusion | 52.7 | #24 of 26 |
| Intrusion-002Windows Enterprise Intrusion | 47.7 | #26 of 26 |
| Intrusion-001macOS Threat Investigation | 63.7 | #24 of 26 |
Models ranked nearby
The models closest to Gemini 3.1 Pro on the overall leaderboard.
| Model | Rank | Score | Cost / task |
|---|---|---|---|
| #22 | 56.4 | $0.90 | |
| #23 | 53.6 | $0.91 | |
| #24 | 50.5 | $4.44 | |
Gemini 3.1 Pro | #25 | 45.3 | $4.63 |
| #26 | 44.8 | $1.77 |
More Google models
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