Benchmark Almanac

ParallelKernelBench

GPT-5.5 32.2% leads since June 2026
Not in model cards

Models replace PyTorch and NCCL reference code with multi-GPU CUDA kernels for 87 problems from codebases such as Megatron-LM and DeepSpeed. Scored on correctness and speed over the baseline.

Default runs use 8 H100 GPUs. Best zero-shot model solved 28 of 87 at launch.

Made by
Together AI and Stanford
Released
June 2026
Kind
GPU kernels
Level
Expert
Scored
Checked automatically
Answers
Code
Tasks
All public
Strongest model tested
GPT-5.5 #20 on the capability index
Last model added
June 2026
Scores refreshed
November 12th, 2026
6
Entries on its own leaderboard, 4 models we track

GPT-5.5 leads with 32.2% among models released by June 2026

Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

The newest model with a score here came out in June 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 32.2 GPT-5.5
  2. 27.6 Gemini 3 Pro [snapshot unspecified]
  3. 23.0 Claude Opus 4.7
  4. 6.90 GLM-5.1
  5. 4.60 GLM-5.2
  6. 2.30 DeepSeek V4 Pro [snapshot unspecified]
  1. 1 GPT-5.5 32.2%
  2. 2 Gemini 3 Pro [snapshot unspecified] 27.6%
  3. 3 Claude Opus 4.7 23%
  4. 4 GLM-5.1 6.90%
  5. 5 GLM-5.2 4.60%
  6. 6 DeepSeek V4 Pro [snapshot unspecified] 2.30%

Source: Official ParallelKernelBench leaderboard

#EntryScoreSettingDateSource
1 GPT-5.5 32.2% mini-swe-agent Apr 2026 Official leaderboard
2 Gemini 3 Pro [snapshot unspecified] 27.6% mini-swe-agent Official leaderboard
3 Claude Opus 4.7 23% mini-swe-agent Apr 2026 Official leaderboard
4 GLM-5.1 6.90% mini-swe-agent Apr 2026 Official leaderboard
5 GLM-5.2 4.60% mini-swe-agent Jun 2026 Official leaderboard
6 DeepSeek V4 Pro [snapshot unspecified] 2.30% mini-swe-agent Official leaderboard

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Own leaderboard Not tested since Jun 2026
GPT-5.5 32.2%

Source: Official ParallelKernelBench leaderboard

Scores over time

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% 2026 Near the ceiling (85%) GPT-5.5 Claude Opus 4.7 GLM-5.1 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.5 Claude Opus 4.7

Source: Official ParallelKernelBench leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in AI research

All 104 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 Astra 93.8%
  • KernelBench In use Replace PyTorch operators with faster custom GPU kernels. Scored on correctness and speedup. MiniMax-M3 28.8%
  • 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. Inkling 2 Small 494.3