ITBench
Gemini 3 Pro 58.3% leads since Nov 2025 Not in model cards Agents handle IT automation tasks in Kubernetes environments: site reliability incidents, compliance and security checks, and cloud cost work.
Presented as an oral at ICML 2025. IBM and Kaggle added an ITBench leaderboard in 2025-12.
In the authors’ words
Realizing the vision of using AI agents to automate critical IT tasks depends on the ability to measure and understand effectiveness of proposed solutions. We introduce ITBench, a framework that offers a systematic methodology for benchmarking AI agents to address real-world IT automation tasks. Our initial release targets three key areas: Site Reliability Engineering (SRE), Compliance and Security Operations (CISO), and Financial Operations (FinOps). The design enables AI researchers to understand the challenges and opportunities of AI agents for IT automation with push-button workflows and interpretable metrics. ITBench includes an initial set of 94 real-world scenarios, which can be easily extended by community contributions. Our results show that agents powered by state-of-the-art models resolve only 13.8% of SRE scenarios, 25.2% of CISO scenarios, and 0% of FinOps scenarios. We expect ITBench to be a key enabler of AI-driven IT automation that is correct, safe, and fast.
- Level
- Expert Specialists with years of training, often over hours of work
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Agent task Many steps in a terminal, browser, desktop, app, game or robot.
Gemini 3 Pro leads with 58.3% among models released by Nov 2025
Best score per model from the benchmark's own leaderboard, read on 2 Nov 2026. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in Nov 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 1 Gemini 3 Pro 58.3%
- 2 GPT-5.1 55.2%
- 3 Claude Opus 4.5 52.1%
- 4 GPT-5 51.9%
- 5 o3 51.7%
- 6 Gemini 2.5 Flash Sep 2025 51.7%
- 7
Qwen3-235B-A22B 46% - 8 Claude Sonnet 4.5 45.8%
- 9 Gemini 2.5 Pro Jun 2025 42.3%
- 10 Claude Haiku 4.5 42.1%
- 11 Grok 4.1 Fast reasoning 39%
- 12
Mistral Small 3.1 32.9% - 13
DeepSeek-R1 May 2025 23.3%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Gemini 3 Pro | 58.3% | Nov 2025 | Official leaderboard | |
| 2 | GPT-5.1 | 55.2% | Nov 2025 | Official leaderboard | |
| 3 | Claude Opus 4.5 | 52.1% | Nov 2025 | Official leaderboard | |
| 4 | GPT-5 | 51.9% | Aug 2025 | Official leaderboard | |
| 5 | o3 | 51.7% | Apr 2025 | Official leaderboard | |
| 6 | Gemini 2.5 Flash Sep 2025 | 51.7% | Sep 2025 | Official leaderboard | |
| 7 | Qwen3-235B-A22B | 46% | Apr 2025 | Official leaderboard | |
| 8 | Claude Sonnet 4.5 | 45.8% | Sep 2025 | Official leaderboard | |
| 9 | Gemini 2.5 Pro Jun 2025 | 42.3% | Jun 2025 | Official leaderboard | |
| 10 | Claude Haiku 4.5 | 42.1% | Oct 2025 | Official leaderboard | |
| 11 | Grok 4.1 Fast | 39% | reasoning | Nov 2025 | Official leaderboard |
| 12 | Mistral Small 3.1 | 32.9% | Mar 2025 | Official leaderboard | |
| 13 | DeepSeek-R1 May 2025 | 23.3% | May 2025 | Official leaderboard |
5 models have held number one since its release in Feb 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No lab model card reports it yet
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark.
More in Terminal agents
- Terminal-Bench 4.0 In use Agents complete 66 hard tasks in containerized terminals across software, ML, science, security, and operations. Test scripts verify each result, scored as resolution rate. Claude Opus 5.5 64.8%
- SkillsBench In use 86-87 containerized expert tasks in 11 domains, run with and without Agent Skills. Verifier tests give pass rate and skill lift. GPT-5.5 67.3%
- Terminal-Bench Hard In use Agents complete 44 hard tasks from Terminal-Bench Core in the Terminus 2 harness. Artificial Analysis scores pass@1 averaged over 3 repeats. Gemma 4 31B IT 36%
- Harbor-Index In use Agents solve about 80 hard tasks drawn from 29 benchmarks run through Harbor adapters, such as HLE, GSO and SWE-bench Pro. Each task keeps its source verifier. GPT-5.5 28.1%
- CompileBench Not in model cards Agents build real open-source projects through dependency problems, legacy toolchains and complex build systems, for example compiling 22-year-old code. Claude Opus 4.1 100%
- Long-Horizon-Terminal-Bench 2.0 Not in model cards Agents work for up to 3 hours per task on 77 container tasks, including 30 tasks that rebuild a scientific tool from its outputs. Hidden verifiers give partial-credit rewards. GPT-6 Astra 69.2%