Aspire
Qwen3.5-9B 25.6% Agent gets only a vague capability goal and must choose data, training and self-checks to evolve weights or harness. Scored on 520 hidden items.
Hidden eval spans 6 goals. Weight-level gains were rare. The arXiv page lists no affiliations.
- Made by
- ByteDance Seed et al.
- Released
- August 2026
- Kind
- AI research tasks
- Level
- Research frontier
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- Kept private
- Strongest model tested
- Qwen3.5-9B #127 on the capability index
- Last model added
- February 2026
- Scores refreshed
- November 12th, 2026
2
Models scored on its own leaderboard
Qwen3.5-9B leads with 25.6%
Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.
- 1 Qwen3.5-9B Final-only evolution 25.6%
- 2 Qwen3.5-4B Final-only evolution 18.6%
Source: Official Aspire leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Qwen3.5-9B | 25.6% | Final-only evolution | Feb 2026 | Official leaderboard |
| 2 | Qwen3.5-4B | 18.6% | Final-only evolution | Feb 2026 | Official 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
Source: Official Aspire 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
- 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