Interactive Program Induction - LM only (CodeARC) - 1 Seed: leaderboard
Full anonymized CodeARC split, 5independentseeds, 30I/O budget including1seedinvocations. CodeARC may issue2equivalencequeries; EIGnone. Mokav correctness tester fixedQwen2.5-32B; sharedinput distributionconditionedon10benchmarkseedexamples. All evaluatedLMs instruction-tuned; methodsremain separate. Metric: Program accuracy (0–1). Source: https://arxiv.org/html/2611.18485v1
Metric: Program accuracy (0–1). Source: arxiv.org. Saturation forecast: Around February 2027. 6 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 32B Instruct | 0.25 | #1257 |
| 2 | Ministral-8B-Instruct-2410 | 0.239 | #4569 |
| 3 | Qwen 2.5 7B Instruct | 0.148 | #2706 |
| 4 | Llama 3.2 3B Instruct | 0.134 | #7230 |
| 5 | Llama 3.1 8B Instruct | 0.129 | #4576 |
| 6 | OLMo 3 7B Instruct | 0.064 | #6916 |
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-lm-only-codearc-1-seed · How It Works · Data refreshed daily, snapshot 2026-11-17.