agents benchmark
QwenClawBench
QwenClawBench is a real-user-distribution Claw agent benchmark for evaluating coding agents on realistic developer tasks.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
QwenClawBench leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 61.8% | 100.0% | 1 | C |
QwenClawBench highlights
The top published results on this benchmark's own scale.
What is QwenClawBench?
Definition and scoring fields from the benchmark registry.
QwenClawBench is a real-user-distribution Claw agent benchmark for evaluating coding agents on realistic developer tasks.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- QwenClawBench
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- qwenclawbench|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about QwenClawBench.
Which model scores highest on QwenClawBench?
Qwen3.7-Plus is currently ranked first with 61.8%.
What does QwenClawBench measure?
QwenClawBench is a real-user-distribution Claw agent benchmark for evaluating coding agents on realistic developer tasks.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 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.