agents benchmark
ZClawBench
ZClawBench evaluates Claw-style agent task execution quality, measuring a model's ability to autonomously complete complex multi-step coding tasks in real-world environments.
Updated Aug 7, 2026
Published models4
Registry coverage4
MetricScore
EvidenceB
ZClawBench leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 64.3% | 100.0% | 4 | C | |
| 2 | ZA | 57.6% | 66.7% | 4 | C | |
| 3 | AC | 53.4% | 33.3% | 4 | C | |
| 4 | AC | 52.6% | 0.0% | 4 | C |
Score distribution
Top published rows on the benchmark's original scale.
ZClawBench highlights
The top published results on this benchmark's own scale.
What is ZClawBench?
Definition and scoring fields from the benchmark registry.
ZClawBench evaluates Claw-style agent task execution quality, measuring a model's ability to autonomously complete complex multi-step coding tasks in real-world environments.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- ZClawBench
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- zclawbench|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about ZClawBench.
Which model scores highest on ZClawBench?
Qwen3.7 Max is currently ranked first with 64.3%.
What does ZClawBench measure?
ZClawBench evaluates Claw-style agent task execution quality, measuring a model's ability to autonomously complete complex multi-step coding tasks in real-world environments.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
4 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.