OpenRSI Index Learnability-Aware Long/Short CoT Adaptation
Agents adapt mathematical reasoning examples under a fixed training budget. The score is accuracy across five math benchmarks.
One track of OpenRSI Index. The OpenRSI Index record keeps lab scores that combine tracks.
- Released
- September 2026
- Kind
- AI research tasks
- Level
- Research frontier
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Strongest model tested
- Claude Fable 5 #11 on the capability index
- Last model added
- July 2026
- Scores refreshed
- November 12th, 2026
Claude Fable 5 leads with 47.5%
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 Claude Fable 5 47.5%
- 2 GPT-5.6 Sol xhigh 46.1%
Source: Official OpenRSI Index Learnability-Aware Long/Short CoT Adaptation leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5 | 47.5% | Claude Code | Jun 2026 | Official leaderboard |
| 2 | GPT-5.6 Sol | 46.1% | xhigh, Codex | Jul 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.
Source: Official OpenRSI Index Learnability-Aware Long/Short CoT Adaptation 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