CodeSpecBench-Repo - Correctness: leaderboard
CodeSpecBench (2026) asks models to write executable precondition and postcondition functions that specify the intended behaviour of a program; the repository-level set uses the 500 SWE-bench Verified issues, injecting the specifications around the issue-relevant functions. Correctness, the share of specifications that accept every valid test, in percent; higher is better.
Metric: Correctness (%), the share of generated executable pre/postcondition specifications that accept every valid test, on CodeSpecBench-Repo (500 SWE-bench Verified issues; specifications injected around the issue-relevant functions, trigger tests on the fixed and buggy versions with UTBoost-augmented tests); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Sonnet 4.5 | Thinking | 37.4 | #267 |
| 2 | Gemini 2.5 Pro | 30.8 | #280 | |
| 3 | DeepSeek V3.2 | Non-reasoning | 20.2 | #425 |
| 4 | GPT-5 Mini | 19.6 | #373 | |
| 5 | GPT-5 | 18.8 | #185 | |
| 6 | QwQ-32B | 10.6 | #913 | |
| 7 | GPT-OSS-20B | 9.4 | #1188 | |
| 8 | Gemini 2.5 Flash | 9.2 | #466 | |
| 9 | Qwen 3 32B | 8.8 | #983 | |
| 10 | GPT-OSS-120B | 8.6 | #712 | |
| 11 | Qwen 3 14B | 6 | #1284 | |
| 12 | Qwen 3 8B | 2 | #1890 | |
| 13 | Qwen 3 4B | 0.6 | #2379 | |
| 14 | Qwen 3 1.7B | Non-reasoning | 0.2 | #5913 |
| 15 | Qwen 3 0.6B | 0 | #8357 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=codespecbench-repo-correctness · How It Works · Data refreshed daily, snapshot 2026-11-22.