KernelBench HardBrowse 284 families
KernelBench Hard
Can the model complete substantial programming work under this benchmark's agent setup?
Version / measure
- Domain
- Coding
- Ranked models
- 1
- Reported values
- 1
- Reports
- 1 · lab
- Direction
- Higher is better
- Status
- Version not specified
Rankings
Best reported score per model across effort settings
| # | Model | Best setting | Score |
|---|---|---|---|
| 1 | MiniMax M3MiniMaxOW | reportedcost n/a1 value · Jun 1 · source | 28.8% |
Effort curve
Score vs. reported cost. Lines connect complete sweeps only.
No cost-linked effort sweep for this version.
Definition and comparison boundarylimited methodology
Can the model complete substantial programming work under this benchmark's agent setup?
Software implementation, debugging, or repository work under the published evaluation protocol. Higher is better. The value is the percentage reported in this lab's table.
Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.
Claude Code on NVIDIA Blackwell GPUs; score is the average of nine questions relative to theoretical peak.
Method / source ↗