agents benchmark
CL-bench
CL-bench is an open-source benchmark with its own data and rubrics for evaluating models on coding and agentic tasks, scored using a setup fully aligned with the official procedure.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
CL-bench leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | TE | 23.8% | 100.0% | 2 | C | |
| 2 | MI | 20.5% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
CL-bench highlights
The top published results on this benchmark's own scale.
What is CL-bench?
Definition and scoring fields from the benchmark registry.
CL-bench is an open-source benchmark with its own data and rubrics for evaluating models on coding and agentic tasks, scored using a setup fully aligned with the official procedure.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- CL-bench
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- cl-bench|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about CL-bench.
Which model scores highest on CL-bench?
Hy3 is currently ranked first with 23.8%.
What does CL-bench measure?
CL-bench is an open-source benchmark with its own data and rubrics for evaluating models on coding and agentic tasks, scored using a setup fully aligned with the official procedure.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.