VeriContest - CodeGen (Specification): leaderboard

VeriContest (2026) is a verifiable code generation benchmark of 946 LeetCode and Codeforces problems in Rust with Verus, each with expert-validated specifications, reference code and Verus-checked proofs. This task asks for executable Rust code from the formal specification alone, checked against the test suites; pass@1 in percent, higher is better.

Metric: Code generation pass@1 (%) from the ground-truth Verus specification alone (spec2code): share of problems whose generated Rust code passes the test suites, on the 946 VeriContest competitive-programming problems (690 LeetCode, 256 Codeforces) in Rust with Verus, one-shot prompting with a Verus-Bench example, temperature 0 where the API exposes it (provider default for GPT-5.5 and Claude Opus 4.7); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 10 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Claude Sonnet 4.674.31#173
2Gemini 3.1 Pro (Preview)68.18#99
3Claude Opus 4.767.76#85
4GPT-5.5 (2026-04-23)67.65#39
5DeepSeek V4 Pro62.68#196
6DeepSeek V4 Flash59.51#267
7GPT-5.4 Mini (2026-03-17)51.59#288
8Qwen 3.6 27B41.44#351
9Gemini 3 Flash (Preview)31.92#152
10GLM-4.7 Flash17.65#1349

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

Interactive version: theaggregate.ai/benchmark?slug=vericontest-codegen-specification · How It Works · Data refreshed daily, snapshot 2026-11-21.