Skip to main content

Benchmark profile

KernelBench Hard H100 (KernelBench)

An agentic GPU-kernel benchmark that measures how much of the hardware roofline a model's correct, audit-clean kernels reach on six demanding CUDA and Triton problems.

How we show KernelBench

We mirror the KernelBench Hard H100 PCIe board from kernelbench.com. The visible score is mean peak fraction of roofline (valid cells) across 6 GPU-kernel problems; failed and audit-flagged cells do not enter that mean.

This is an independent agent benchmark, not the Stanford KernelBench project leaderboard. Rows combine a model, an agent harness, long-running GPU sessions, and human audit decisions, so the table stays display only.

14 agent rows6 kernel problemsH100 PCIe11 audit flags trackedDisplay only

Mean peak fraction of roofline on KernelBench — July 17, 2026 snapshot

BenchLM mirrors the published mean peak fraction of roofline view for KernelBench. Claude Fable 5 leads the public snapshot at 23.9% , followed by Grok 4.5 (22.9%) and Kimi K3 (20.9%). BenchLM does not use these results to rank models overall.

14 modelsCodingCurrentDisplay onlyUpdated July 17, 2026 snapshot

Mean peak fraction of roofline table (14 models)

Score
1
Claude Fable 5Anthropic · Closed
23.9%
2
Grok 4.5xAI · Closed
22.9%
3
Kimi K3Moonshot AI · Closed
20.9%
4
Claude Opus 4.8Anthropic · Closed
20.9%
5
Kimi K3Moonshot AI · Closed
17.9%
6
Hy3Tencent · Open weight
14.7%
7
GPT-5.5OpenAI · Closed
13.9%
8
MiniMax M3MiniMax · Open weight
13.4%
9
GLM-5.2Z.AI · Open weight
10.7%
10
LongCat-2.0Meituan · Open weight
10.4%
11
Kimi K2.7 CodeMoonshot AI · Open weight
10.4%
12
9.2%
13
Hy3Tencent · Open weight
5.2%
14
DeepSeek V4 ProDeepSeek · Open weight
3.5%

The published KernelBench snapshot is tightly clustered at the top: Claude Fable 5 sits at 23.9%, while the third row is only 2.9 points behind. The broader top-10 spread is 13.5 points, so the benchmark still separates strong models even when the leaders cluster.

14 models have been evaluated on KernelBench. The benchmark falls in the Coding category. This category carries a 20% weight in BenchLM.ai's overall scoring system. KernelBench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About KernelBench

Year

2026

Tasks

6 GPU-kernel optimization problems

Format

Mean peak fraction of hardware roofline over valid cells

Difficulty

Agentic GPU systems engineering

The mirrored board comes from the independent kernelbench.com Hard suite, not the Stanford KernelBench project. One long-running agent session tackles each problem. The visible score averages peak fraction of roofline over valid cells; failed and audit-flagged cells are excluded from that mean. We keep the benchmark display only because harness, hardware, and audit state are inseparable from the score.

BenchLM freshness & provenance

Version

KernelBench 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does KernelBench measure?

An agentic GPU-kernel benchmark that measures how much of the hardware roofline a model's correct, audit-clean kernels reach on six demanding CUDA and Triton problems.

Which model leads the published KernelBench snapshot?

Claude Fable 5 currently leads the published KernelBench snapshot with 23.9% mean peak fraction of roofline. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on KernelBench?

14 AI models are included in BenchLM's mirrored KernelBench snapshot, based on the public leaderboard captured on July 17, 2026 snapshot.

Last updated: July 17, 2026 snapshot · mirrored from the public benchmark leaderboard

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.