RLTasksby ulam.ai
Models / Qwen

Qwen / MODEL EVIDENCE

Qwen2.5-Coder-32B-Instruct

8 benchmarks · 12 observations · 8 sources · released 2024-11-21

Scores at a glance

8 benchmarks · large dot: Qwen2.5-Coder-32B-Instruct; small dots: closest models where reported

Aider coding benchmarks ↗16.4%
3.688

Qwen2.5-Coder-32B-Instruct · Aider coding benchmarks · Polyglot · percent correct ↗

4 more reported results

8% · Qwen2.5-Coder-32B-Instruct · Aider coding benchmarks · Polyglot · percent correct · Epoch AI · Aider polyglot ↗

16.4% · Qwen2.5-Coder-32B-Instruct · Aider coding benchmarks · Polyglot · percent correct · Aider code editing benchmark ↗

8% · Qwen2.5-Coder-32B-Instruct · Aider coding benchmarks · Polyglot · percent correct · Aider code editing benchmark ↗

71.4% · Qwen2.5-Coder-32B-Instruct · Aider coding benchmarks · Refactoring · percent correct · Aider refactoring benchmark ↗

GSM8K ↗93%
4.494.5

Qwen2.5-Coder-32B-Instruct · GSM8K · EM · % ↗

LiveBench ↗46.23%
22.0882.35

Qwen2.5-Coder-32B-Instruct · LiveBench · Global average · % ↗

CodeElo ↗575 Elo
211578

Qwen2.5-Coder-32B-Instruct · CodeElo · Overall competition Elo · main comparison ↗

HumanEval+ ↗87.2%
1.889

Qwen2.5-Coder-32B-Instruct · HumanEval+ · Pass@1 · EvalPlus · official result data ↗

MBPP+ ↗77%
7.580.2

Qwen2.5-Coder-32B-Instruct · MBPP+ · Pass@1 · EvalPlus · official result data ↗

HumanEval ↗92.1%
2.496.3

Qwen2.5-Coder-32B-Instruct · HumanEval · Pass@1 · EvalPlus · official result data ↗

ProcessBench ↗56.1 F1 points
5.187.9

Qwen2.5-Coder-32B-Instruct · ProcessBench · Average F1 · original comparison ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

How similarity is measured

Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. Aider code editing benchmark ↗

    Paul Gauthier, Aider contributors

  2. Aider LLM Leaderboards — Polyglot coding benchmark ↗

    Aider

  3. Aider refactoring benchmark ↗

    Paul Gauthier, Aider contributors

  4. Qwen2.5-Coder Technical Report ↗

    Hui, Binyuan, Yang, Jian, Cui, Zeyu, Yang, Jiaxi, Liu, Dayiheng, Zhang, Lei et al. · 2024

    All 24 authors

    Hui, Binyuan, Yang, Jian, Cui, Zeyu, Yang, Jiaxi, Liu, Dayiheng, Zhang, Lei, Liu, Tianyu, Zhang, Jiajun, Yu, Bowen, Lu, Keming, Dang, Kai, Fan, Yang, Zhang, Yichang, Yang, An, Men, Rui, Huang, Fei, Zheng, Bo, Miao, Yibo, Quan, Shanghaoran, Feng, Yunlong, Ren, Xingzhang, Ren, Xuancheng, Zhou, Jingren, Lin, Junyang

  5. ProcessBench: Identifying Process Errors in Mathematical Reasoning — published result table ↗

    Zheng, Chujie, Zhang, Zhenru, Zhang, Beichen, Lin, Runji, Lu, Keming, Yu, Bowen et al. · 2024

    All 9 authors

    Zheng, Chujie, Zhang, Zhenru, Zhang, Beichen, Lin, Runji, Lu, Keming, Yu, Bowen, Liu, Dayiheng, Zhou, Jingren, Lin, Junyang

  6. CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings — published result table ↗

    Shanghaoran Quan, Jiaxi Yang, Bowen Yu, Bo Zheng, Dayiheng Liu, An Yang et al. · 2025

    All 17 authors

    Shanghaoran Quan, Jiaxi Yang, Bowen Yu, Bo Zheng, Dayiheng Liu, An Yang, Xuancheng Ren, Bofei Gao, Yibo Miao, Yunlong Feng, Zekun Wang, Jian Yang, Zeyu Cui, Yang Fan, Yichang Zhang, Binyuan Hui, Junyang Lin

  7. Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation — published result table ↗

    Liu, Jiawei, Xia, Chunqiu Steven, Wang, Yuyao, Zhang, Lingming · 2023

  8. LiveBench — model evaluation leaderboard ↗

    LiveBench Team

Names used in source tables

Qwen2.5-Coder-32B-Instruct