RecentsView All

Your evaluations

Sign in to run benchmarks and follow your results here.

Benchgen

Overview Leaderboard Evaluations Phases

BigCodeBench-Hard — Results

Rank	Model	Score
1	qwen2-5-coder-32b-instruct	0.27

B

BigCodeBench-Hard — Leaderboard

1 phaseActive

BigCodeBench-Hard Leaderboard

No self-reported entries.

About

Challenging subset of 148 BigCodeBench tasks requiring complex multi-library function calls across 7 domains.

Pages

Phases: 1Active
Participants: 1
Submissions: 1
Last Modified: Jul 24, 2026