Kernel Engineering
Task 19 / 47
MLA
This task focuses on implementing and tuning a multi-head attention–style (MLA) GPU kernel for correctness and strong throughput or latency on the target device. It exercises memory coalescing, register/shared-memory pressure, and launch configuration. The scorer combines numerical checks with performance metrics, reflecting operator-level HPC engineering.
Model leaderboard
| # | Participant | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro Preview | 100.0 |
| 2 | GPT-5.4 | 90.3 |
| 3 | Claude Opus 4.6 | 79.8 |
| 4 | GLM-5 | 1.5 |
| 5 | SEED 2.0 Pro | 1.5 |
| 6 | Grok 4.20 | 1.5 |
| 7 | Qwen3 Coder Next | 0.0 |
| 8 | DeepSeek V3.2 | 0.0 |
Framework leaderboard
| # | Participant | Score |
|---|---|---|
| 1 | Claude Opus 4.6 + OpenEvolve | 100.0 |
| 2 | Claude Opus 4.6 + ABMCTS | 99.5 |
| 3 | Claude Opus 4.6 + ShinkaiEvolve | 93.7 |
| 4 | GPT-OSS + ShinkaiEvolve | 7.4 |
| 5 | GPT-OSS + OpenEvolve | 7.3 |
| 6 | GPT-OSS + ABMCTS | 0.0 |
Score is the normalized score for this task (0–100, higher is better).