agents benchmark
Kernel Bench L3 Leaderboard
Kernel Bench L3 evaluates agentic GPU kernel optimization across 50 problems. Qwen reports two metrics for this benchmark: median per-problem speedup over the PyTorch eager reference and the fraction of problems faster than torch.compile.
Updated Aug 17, 2026
Models1
Model coverage1
MetricScore
EvidenceB
Kernel Bench L3 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score96.0% | Percentile100.0% | Participants1 | EvidenceC | Evaluated |
Kernel Bench L3 Highlights
The leading models and scores on this benchmark.
The Top AI Models for Kernel Bench L3
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis kernel bench l3 AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01ACQwen3.7 MaxAlibaba Cloud / Qwen Team
- Score
- 96.0%
- Price
- $2.5 input / $7.5 output per 1M tokens
- Speed
- Up to 5.8 tok/s via Together
Strengths
- Ranks #1 of 1 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures Kernel Bench L3, not total model capability
Selection summary
Best AI Models for Kernel Bench L3
Qwen3.7 Max currently leads Kernel Bench L3 with 96.0%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is Kernel Bench L3?
What Kernel Bench L3 measures and how its scores work.
Kernel Bench L3 evaluates agentic GPU kernel optimization across 50 problems. Qwen reports two metrics for this benchmark: median per-problem speedup over the PyTorch eager reference and the fraction of problems faster than torch.compile.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Kernel Bench L3
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- kernel-bench-l3|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Kernel Bench L3.
Which model scores highest on Kernel Bench L3?
Qwen3.7 Max is currently ranked first with 96.0%.
What does Kernel Bench L3 measure?
Kernel Bench L3 evaluates agentic GPU kernel optimization across 50 problems. Qwen reports two metrics for this benchmark: median per-problem speedup over the PyTorch eager reference and the fraction of problems faster than torch.compile.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.