SREGym-Lite
Agents diagnose and mitigate failures in running services on a Kubernetes cluster.
The suite selects 17 incidents with different failure mechanisms that can run in a small local cluster.
- Made by
- SREGym team
- Released
- July 2026
- Kind
- Terminal tasks
- Level
- Expert
- Scored
- Settled by events
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Terminal, Kubernetes
- Refresh
- One fixed set
- Run by
- Anyone
- Based on
- A version of another benchmark
- In views
- Agents
- Strongest model tested
- Claude Sonnet 5.5 #9 on the capability index
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
Claude Sonnet 5.5 leads with 81.3%
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.
- 1 Claude Sonnet 5.5 reasoning:high 81.3%
- 2 Claude Haiku 5.5 56.3%
Source: Official SREGym-Lite leaderboard
| # | Model | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | Claude Sonnet 5.5 | 81.3% | reasoning:high, Claude Code 2.1.319 | Sep 2026 | github.com | Official leaderboard |
| 2 | Claude Haiku 5.5 | 56.3% | Claude Code 2.1.318 | Oct 2026 | github.com | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official SREGym-Lite leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Terminal agents
- 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 66.5%
- 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%
- Terminal-Bench 4.1 In use The Terminal-Bench 4.0 tasks with hardened verifiers: agents complete 66 hard tasks in containerized terminals across software, ML, science, security, and operations. Test scripts verify each result, scored as resolution rate. Copilot Fusion 71.2%
- 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%
- Terminal-Bench 2.1 Extended Not in model cards Agents complete long command-line tasks in containers, scored by verification tests. Mercor adds 99 new expert-written tasks to the 89 public ones and reports both scores.
Muse Wonder 54%
- Terminal-Bench Pro Not in model cards Agents solve 400 terminal tasks across eight domains. Harbor distributes the 200 public tasks. Alibaba keeps the other 200 for private evaluation. Claude Opus 4.5 51%
Data audit
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (2 entries).
- Note Models scored Only 2 models we track.
- Pass Newest score The newest is from October 2026, for Claude Haiku 5.5.
- Note Frontier models Only 1 of the top 10 has a score. The strongest tested is Claude Sonnet 5.5 (#9).
- Pass Headroom The best is 81.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on huggingface.co: 2 rows for models we track at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.