Interactive Program Induction - 100 Problems Temperature1 - Exact: leaderboard

Pinned appendix A5.T7; same released instruction-tuned models; exact subset/query/prior protocol in caption. A4T3 three seeds, evaluator rebuiltfromsinglevisibleexample. A5T7 100problems, temp1, three weightingrules. A5T8 100problems, nativeprompttemperatures andfixedselectionrule. A5T9 112sampledprograms, nooraclequeries. No cost/query-count metrics or duplicate Ours columns. Metric: Program accuracy (0–1). Source: https://arxiv.org/html/2611.18485v1

Metric: Program accuracy (0–1). Source: arxiv.org. Saturation forecast: Around November 2027. 6 models tracked. Updated 17 Nov 2026.

Top models

#ModelScoreOverall rank
1Qwen 2.5 32B Instruct0.282#1257
2OLMo 3 7B Instruct0.239#6916
3Llama 3.1 8B Instruct0.18#4576
4Qwen 2.5 7B Instruct0.18#2706
5Ministral-8B-Instruct-24100.159#4569
6Llama 3.2 3B Instruct0.139#7230

No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.

Interactive version: theaggregate.ai/benchmark?slug=interactive-program-induction-100-problems-temperature1-exact · How It Works · Data refreshed daily, snapshot 2026-11-17.