Qwen2.5 Coder 32B Instruct — Benchmarks

Benchmark scores for Qwen2.5 Coder 32B Instruct aggregated from public leaderboards (5 boards), with how it ranks among open models and how it compares with its nearest neighbours. See hardware requirements for what you need to run it.

llmrun Composite Score →

81.9

90% range 76.0–87.8 · from 3 boards

CodingNot enough data yet
Agents83.690% range 76–91
MathNot enough data yet
ScienceNot enough data yet
ReasoningNot enough data yet

Qwen2.5 Coder 32B Instruct coding benchmarks

Writing, editing, and fixing real code — measured by whether the resulting program actually runs and passes tests.

SWE-bench Verified
SWE-bench Verified tests whether a model can resolve real GitHub issues from popular open-source Python projects, scored on the official swebench.com leaderboard as the percentage of human-validated issues actually fixed. It is the headline measure of practical, agentic software-engineering ability — where open-weight models like Qwen3-Coder, GLM-4.6, Kimi K2 and DeepSWE are now competitive with the frontier.
47.0%
47.0%
median 62.2%open leader 75.8%
Overall best: live-SWE-agent + Claude 4.5 Opus medium (20251101) 79.2%
21st percentile · #16 of 20 open · #104 of 162 all
#16 of 20
#104 of 162
Independent
SWE-bench · Jun 2025
Aider Polyglot
The Aider Polyglot benchmark measures real-world coding across several programming languages: the model edits code to solve Exercism exercises, and is scored on whether the final solution actually runs and passes the tests.
16.4%
16.4%
median 45.1%open leader 74.2%
Overall best: GPT 5 (Aug 07, 2025, high) 88.0%
24th percentile · #14 of 18 open · #61 of 69 all
#14 of 18
#61 of 69
Independent
Epoch AI · Nov 2024
SWE-bench Bash Only
SWE-bench Bash Only runs the SWE-bench Verified issues through a minimal, single-tool bash agent — no specialised scaffolding — so the score reflects the model's own agentic coding ability rather than the harness around it. A cleaner, harder read on raw software-engineering skill.
9.0%
9.0%
median 55.4%open leader 63.4%
Overall best: Claude 4.5 Opus (high reasoning) 76.8%
lowest · #9 of 9 open · #48 of 48 all
#9 of 9
#48 of 48
Independent
SWE-bench · Aug 2025

Qwen2.5 Coder 32B Instruct math benchmarks

Symbolic and quantitative problem-solving, from competition math to multi-step calculation.

GSM8K
GSM8K is a classic set of grade-school math word problems requiring several arithmetic reasoning steps. Long a default sanity check for reasoning, top models now score near the ceiling, so it best separates smaller models.
93.0%
93.0%
median 52.3%open leader 94.5%
97th percentile · #3 of 62 open · #3 of 93 all
#3 of 62
#3 of 93
Lab-reported
Epoch AI · Nov 2024

Qwen2.5 Coder 32B Instruct instruction following benchmarks

How precisely a model obeys explicit, verifiable instructions — format, length, and content constraints — and, more broadly, how much people prefer its responses head-to-head in blind human voting.

LMArena Text
Arena (arena.ai, formerly LMArena / Chatbot Arena) ranks models by millions of blind, head-to-head human votes on real prompts. The Arena Score shown here is a Bradley-Terry rating computed with Arena's default style control, so higher means people preferred that model's answers more often — it's a relative rating, not a percentage, so compare it only to other models on this board.
1270.6
1270.6
median 1321.5open leader 1487.1
Overall best: Gemini 4 Argon (High) 1523.9
35th percentile · #122 of 187 open · #301 of 405 all
#122 of 187
#301 of 405
Arena
Arena · Oct 2026

Score vs VRAM in the 24 GB tier

Qwen2.5 Coder 32B Instruct
Other models
Best Score for its VRAM
x: VRAM (GB) · y: llmrun Score

#23 of 35 that fit 24 GB

Each dot is a model at the best quant that fits a 24 GB GPU. The line joins the models with the best Score for their VRAM; a dot below it is beaten by a model that needs no more memory.

Full 24 GB ranking →

Qwen2.5 Coder 32B Instruct vs its neighbours

Same boards for the nearest open models per llmrun Score and the best model that fits 24 GB. The highest score in each row is marked.

Board	Qwen2.5 Coder 32B Instructthis model	Qwen3.8 27Bbest in classQ4_K_M · 18 GB	Phi 4nearest by ScoreQ4_K_M · 13 GB	Qwen2.5 32B Instructnearest by ScoreQ4_K_S · 23 GB	Gemma 3 27B ITnearest by ScoreQ4_K_M · 22 GB
llmrun Score	81.9	122.1	83.9	80.4	79.4
Aider Polyglot	16.4%	—	—	—	4.9%
LMArena Text	1270.6	1437.8	1256.3	—	1365.5
Compare head to head		Compare	Compare	Compare	Compare

Scores aggregated from public benchmark sources (Epoch AI: 2 boards, SWE-bench: 2 boards, Arena: 1 board) — each linked from the benchmark pages. llmrun does not run these benchmarks. Percentiles and ranks are among open models in the llmrun catalogue; the median and leader marks refer to the same field.