CodeSpecBench-Func: leaderboard
CodeSpecBench (2026) asks models to write executable precondition and postcondition functions that specify the intended behaviour of a program; the function-level set uses 2,494 LeetCode problems with online-judge-validated valid and invalid tests. Pass rate, the share of specifications that accept every valid test and reject every invalid one, in percent; higher is better.
Metric: Pass rate (%), the share of generated executable pre/postcondition specifications that are both correct (accept every valid test) and complete (reject every invalid test), on CodeSpecBench-Func (2,494 LeetCode problems; 50 valid and 50 invalid inputs plus valid and model-generated buggy outputs per problem, validated by the online judge); 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 | GPT-5 Mini | 47 | #364 | |
| 2 | Gemini 2.5 Pro | 46.2 | #276 | |
| 3 | GPT-OSS-120B | 42.5 | #704 | |
| 4 | Claude Sonnet 4.5 | Thinking | 40.5 | #261 |
| 5 | GPT-5 | 40.2 | #178 | |
| 6 | GPT-OSS-20B | 37.7 | #1183 | |
| 7 | Gemini 2.5 Flash | 36.5 | #463 | |
| 8 | QwQ-32B | 28.7 | #907 | |
| 9 | Qwen 3 14B | 26.4 | #1269 | |
| 10 | Qwen 3 32B | 25.8 | #972 | |
| 11 | DeepSeek V3.2 | Non-reasoning | 24.3 | #419 |
| 12 | Qwen 3 8B | 16.8 | #1873 | |
| 13 | Qwen 3 4B | 15.5 | #2348 | |
| 14 | Qwen 3 1.7B | 1.2 | #5860 | |
| 15 | Qwen 3 0.6B | 0.2 | #8350 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=codespecbench-func · How It Works · Data refreshed daily, snapshot 2026-11-21.