Benchmark Almanac

GPU Puzzles

Not in model cards

Models implement parallel GPU kernels for 14 puzzles. The port runs each kernel against a reference and rejects serial implementations.

GPT-5 mini scored 0.9048 on 14 hub examples on November 5, 2025. Llama 3.1 70B scored 1.0 on three on March 8, 2026.

Made by
Sasha Rush
Released
July 2022
Kind
GPU kernels
Level
University
Scored
Checked automatically
Answers
Code
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Code → Code
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-5 mini #92 on the capability index
Last model added
August 2025
Scores refreshed
November 20th, 2026
2
Models scored on its own leaderboard

GPT-5 mini leads with 90.5%

Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.

  1. 1 GPT-5 mini 0.1.0, 14 examples 90.5%
  2. 2 GPT-4.1 mini 0.1.0, 14 examples 81%

Source: Official GPU Puzzles leaderboard

#ModelScoreSettingReleasedRun onLinkSource
1 GPT-5 mini 90.5% 0.1.0, 14 examples Aug 2025 Nov 2025 app.primeintellect.ai Official leaderboard
2 GPT-4.1 mini 81% 0.1.0, 14 examples Apr 2025 Nov 2025 app.primeintellect.ai Official leaderboard

GPT-5 mini on the official leaderboard passed 85% in August 2025

That was 37 months after its release. All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) GPT-5 mini GPT-4.1 mini 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) GPT-5 mini GPT-4.1 mini

Source: Official GPU Puzzles leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in AI research

All 164 in AI research
  • PaperBench In use Agent replicates ICML 2024 papers from scratch. LLM judge grades against author-written hierarchical rubrics. Qwen 3.8 Max 93%
  • MLS-Bench In use Agent must invent one algorithmic change in an ML research scaffold whose gain transfers across settings. Scored relative to human baselines. Claude Fable 5.1 50.3%
  • PostTrainBench 1.2 In use CLI agent gets a base model, one H100 and a time budget to post-train it for a target benchmark. Scored on normalized gain. Claude Fable 5.1 44.6%
  • MLE-bench In use Kaggle-style ML engineering competitions. Agent trains models and is scored against competition leaderboards. GPT-6.2 Astra 96.1%
  • PMPP-Hard In use Agents write GPU kernels for 69 tasks that must be correct, and on 48 of them also run within 1.25 times the reference time. The score is the area under the solved-tasks curve over a 10-hour budget, out of 690 task-hours. Kimi K3 0.71
  • KernelBench In use Replace PyTorch operators with faster custom GPU kernels. Scored on correctness and speedup. MiniMax-M3 28.8%

Data audit

All 7 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 pass 4 notes
  • Pass Independent runs Scores from the official leaderboard (2 entries).
  • Note Models scored Only 2 models we track.
  • Note Newest score The newest came 15 months ago, in August 2025, for GPT-5 mini. That’s expected for a saturated test.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5 mini (#92).
  • Note Headroom Saturated. The best is 90.5%, past 85% since August 2025.
Leaderboard import 3 pass
  • Pass Importer We read the board on app.primeintellect.ai: 2 rows for models we track at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check