Qwen2.5 Coder 32B Instruct: benchmark scores, price and ranking

Qwen2.5 Coder 32B Instruct from Qwen ranks #367 of 743 LLMs on the LLMs Tiger aggregate benchmark score (48.3), based on 3 benchmark results captured up to 2026-10-13.

Organisation: Qwen
Type: Open-weight / local model
Open weights: Yes
Released: 2024-11-12 (source: curated)
Context window: 32,768 tokens
Cheapest API price: $0.060 in / $0.200 out per million tokens (via nscale, observed 2026-10-13T21:47Z)
Aggregate rank: #367 of 743 (score 48.3)

Relative to other models, Qwen2.5 Coder 32B Instruct is strongest on Aider Code Editing (#14 of 92) and weakest on Aider Polyglot (#41 of 49).

Across the 3 benchmarks where at least ten models are scored, Qwen2.5 Coder 32B Instruct is in the top 10% on 0 and in the top half on 1.

Its cheapest listed input price, $0.060 per million tokens, is lower than that of 89% of the 427 models with a listed price.

Qwen2.5 Coder 32B Instruct benchmark results

Qwen2.5 Coder 32B Instruct benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
Aider Code Editing	71.4%	#14 of 92	Aider Aider Code Editing leaderboard	2026-10-13
SWE-bench Verified	38.0%	#57 of 73	SWE-bench Verified leaderboard	2026-10-13
Aider Polyglot	16.4%	#41 of 49	Aider polyglot leaderboard	2026-10-13

About Qwen2.5 Coder 32B Instruct

Qwen2.5 Coder 32B Instruct is an open-weight model that can run on your own hardware from Qwen. It was released on 2024-11-12, according to the developer's announcement. It accepts up to 32,768 tokens of input at once. The cheapest API listing we track charges $0.060 per million input tokens and $0.200 per million output tokens, through nscale. We hold 3 benchmark results for it across 1 area, and none is in the top tenth of its board.

Where Qwen2.5 Coder 32B Instruct stands

On our aggregate score, Qwen2.5 Coder 32B Instruct is #367 of 743 ranked models, around the middle of the table. Its score is 48.3; the scale is centred on 50, so it sits 1.7 points below the typical model. That beats 51% of the ranked field. Among the 23 ranked Qwen models it is #11. The next one up is SWE-agent-LM-32B at 48.5. The next one down is Qwen2.5 (7B + 72B) at 48.2.

Qwen2.5 Coder 32B Instruct, benchmark by benchmark

Aider Code Editing puts Qwen2.5 Coder 32B Instruct at 71.4%, #14 of 92. That beats 85% of the models tested, but 12.8 points short of Claude 3.5-Sonnet-20241022 (84.2%). The results either side are gpt-4o-2024-11-20 (71.4%) and DeepSeek Chat V2 0628 (69.9%). It covers Aider official benchmark. The board median is 55.6%, so Qwen2.5 Coder 32B Instruct is 15.8 points above it. Source: Aider Aider Code Editing leaderboard, captured 2026-10-13.

Qwen2.5 Coder 32B Instruct lands below the middle on SWE-bench Verified: 38.0%, #57 of 73, with 77% of the field scoring higher. Claude Opus 4.7 (max) leads at 83.5%; the closest result above is DevStral Small 2507 at 38.0%. It covers real GitHub issues resolved. The board median is 56.4%, so Qwen2.5 Coder 32B Instruct is 18.4 points below it. Source: SWE-bench Verified leaderboard, captured 2026-10-13.

Aider Polyglot is a weak spot. Qwen2.5 Coder 32B Instruct scores 16.4%, #41 of 49, behind 82% of the models measured. The leader, gemini-2.5-pro-preview-06-05, reaches 83.1%. It covers edits across 6 languages (225 exercises). The board median is 44.9%, so Qwen2.5 Coder 32B Instruct is 28.5 points below it. Source: Aider polyglot leaderboard, captured 2026-10-13.

Strengths and weaknesses

Software engineering: uneven, ahead of 41% of the field on average across 3 benchmarks. Its best board here is Aider Code Editing (#14 of 92) and its weakest is Aider Polyglot (#41 of 49).

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so Qwen2.5 Coder 32B Instruct costs less than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), DeepSeek V4 Flash 0731 (max) ($0.016, 53.1). Similar scores cost more on DeepSeek-R1-Distill-Qwen-14B ($0.070) and Gemma 4 26B A4B ($0.076).

Release history

The Qwen model released before it was Qwen2.5-VL-72B-Instruct on 2024-09-19, which scores 47.6. The next one was Qwen3-Coder-30B-A3B-Instruct on 2025-07-31, at 52.7.

Reading these numbers

The 3 scores on this page come from 3 sources: Aider Aider Code Editing leaderboard (1), Aider polyglot leaderboard (1), SWE-bench Verified leaderboard (1). 3 of them come from an official leaderboard and 0 from datasets or third-party runs. With 3 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#364 MiMo-7B-RL (48.3)
#365 gemini-2.0-flash-02-05 (48.3)
#366 Ring-2.6-1T (48.3)
#368 mini-SWE-agent + Gemini 3.8 Flash (48.3)
#369 DevStral Small 2507 (48.3)
#370 ernie-5.1 (48.3)