CoRE (Code Reasoning) - IO: leaderboard
Metric: Reasoning Consistency Score (RCS, %) with standard input-output prompting: 60 HumanEval and LiveCodeBench problems with 255 expert-verified functionally equivalent implementations and intermediate-state probes; per problem the score is the strict output consistency (every implementation and test predicted correctly, 0 or 1) times the share of intermediate probes answered correctly, averaged over problems; higher is better. Source: arxiv.org. Saturation forecast: Around May 2028. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3.2 | 40.49 |
| 2 | DeepSeek R1 | 20.6 |
| 3 | GPT-5 | 15.93 |
| 4 | O3 | 8.9 |
| 5 | Claude 3.7 Sonnet | 6.81 |
| 6 | Qwen 3 235B A22B | 0.27 |
Interactive version: theaggregate.ai/benchmark?slug=core-code-reasoning-io · How It Works · Data refreshed daily, snapshot 2026-10-07.