SRE Skills Bench: leaderboard
SRE Skills Bench — average accuracy across cloud and site-reliability-engineering tasks (AWS services, Kubernetes, networking).
Metric: Average (%). Source: sreskillsbench.com. Saturation forecast: Estimated already saturated. 23 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 98.8 | #58 |
| 2 | GPT-5.4 | 98.3 | #79 |
| 3 | GPT-5.5 (High) | 98.3 | #31 (GPT-5.5) |
| 4 | Claude Opus 4.7 | 98.2 | #49 |
| 5 | GPT-5.3 Codex | 98 | #69 |
| 6 | Gemini 3 Pro | 96.7 | #80 |
| 7 | GPT-5.2 Pro | 96.5 | #61 |
| 8 | Kimi K2.5 | 95.9 | #144 |
| 9 | Claude Opus 4.6 | 94.7 | #63 |
| 10 | Claude Opus 4.5 | 94.6 | #83 |
| 11 | GPT-5.2 | 93.3 | #110 |
| 12 | GPT-5.1 Codex Max | 92.5 | #100 |
| 13 | Claude Sonnet 4.6 | 90.4 | #90 |
| 14 | GPT-5.1 | 89.6 | #135 |
| 15 | GPT-5 | 86.9 | #98 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=sre-skills-bench · How It Works · Data refreshed daily, snapshot 2026-10-20.