Enter opens the highlighted result. Esc closes.

R1 0528 vs Qwen2.5 Coder 32B Instruct

Updated October 21, 2026. 28 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace R1 0528 Replace Qwen2.5 Coder 32B Instruct
R1 0528DeepSeek
Coding
71.4
Overall
13.1
Output $/M
$2.15
28
Qwen2.5 Coder 32B InstructQwen
Coding
30.5
Overall
6.7
Output $/M
$1.00
0
vs boards won of 28 shared

Decision reading

Pick R1 0528 for coding: it scores 71.4 on the Vibe Coding Index against 30.5 for Qwen2.5 Coder 32B Instruct, though on 1 benchmark against 2.

Pick Qwen2.5 Coder 32B Instruct when output tokens cost 2.1x less.

Model AR1 0528DeepSeek71.4/1001 independent benchmarkNo cost per solved taskModel BQwen2.5 Coder 32B InstructQwen30.5/1002 independent benchmarksNo cost per solved task
Shared results
28
R1 0528 only
31
Qwen2.5 Coder 32B Instruct only
7
Like-for-like categories
6 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
R1 0528 71.4 from 1 benchmark, Qwen2.5 Coder 32B Instruct 30.5 from 2 benchmarks.
Widest category
Coding, 39.2 points apart on average over 4 shared benchmarks.
Widest single gap
Aider polyglot: R1 0528 71.4% against Qwen2.5 Coder 32B Instruct 16.4%, 55.0 points apart on a 0 to 100 scale.
Output price
R1 0528 $2.15 against Qwen2.5 Coder 32B Instruct $1.00 per million output tokens, 2.1x apart.
Context window
R1 0528 takes 164K tokens, Qwen2.5 Coder 32B Instruct 33K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryR1 0528BarsQwen2.5 Coder 32B InstructTies
Coding40
Intelligence10
Reasoning50
Math20
Knowledge50
General110
All shared boards280
CodingLike-for-likeFour of these boards feed the Vibe Coding Index40
Coding benchmarks for R1 0528 and Qwen2.5 Coder 32B Instruct
BenchmarkR1 0528Qwen2.5 Coder 32B InstructLeader
Aider polyglot71.4%16.4%R1 0528
SWE-bench VerifiedNot measured47.0%Only Qwen2.5 Coder 32B Instruct measured
LiveCodeBench (Artificial Analysis run)77.0%29.5%R1 0528
Terminal-Bench Hard (Artificial Analysis run)15.9%Not measuredOnly R1 0528 measured
WeirdML41.6%Not measuredOnly R1 0528 measured
ALE-Bench804.1Not measuredOnly R1 0528 measured
LMArena Text: coding14271276R1 0528
LMArena Text: software and IT14351261R1 0528
Neither model has a result on the other 30 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for R1 0528 and Qwen2.5 Coder 32B Instruct
BenchmarkR1 0528Qwen2.5 Coder 32B InstructLeader
AA Intelligence Index13.16.7R1 0528
Epoch Capabilities IndexNot measured119.5Only Qwen2.5 Coder 32B Instruct measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
Agentic work benchmarks for R1 0528 and Qwen2.5 Coder 32B Instruct
BenchmarkR1 0528Qwen2.5 Coder 32B InstructLeader
τ²-Bench Telecom36.5%Not measuredOnly R1 0528 measured
METR time horizons53.8%Not measuredOnly R1 0528 measured
DeepResearch Bench35.1%Not measuredOnly R1 0528 measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
Reasoning benchmarks for R1 0528 and Qwen2.5 Coder 32B Instruct
BenchmarkR1 0528Qwen2.5 Coder 32B InstructLeader
GPQA Diamond (Artificial Analysis run)81.3%41.7%R1 0528
Humanity's Last Exam (Artificial Analysis run)15.8%3.5%R1 0528
GPQA Diamond (Epoch AI run)76.3%Not measuredOnly R1 0528 measured
ARC-AGI21.2%Not measuredOnly R1 0528 measured
ARC-AGI-21.1%Not measuredOnly R1 0528 measured
SimpleBench40.8%Not measuredOnly R1 0528 measured
LMArena Text: hard prompts14151251R1 0528
LMArena Text: expert13941221R1 0528
LMArena Text: hard prompts in English14221269R1 0528
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for R1 0528 and Qwen2.5 Coder 32B Instruct
BenchmarkR1 0528Qwen2.5 Coder 32B InstructLeader
AA Math Index76.0Not measuredOnly R1 0528 measured
AIME 2025 (Artificial Analysis run)76.0%Not measuredOnly R1 0528 measured
OTIS Mock AIME66.4%Not measuredOnly R1 0528 measured
MATH level 596.6%Not measuredOnly R1 0528 measured
GSM8KNot measured93.0%Only Qwen2.5 Coder 32B Instruct measured
LMArena Text: math14001251R1 0528
LMArena Text: mathematical work14151243R1 0528
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for R1 0528 and Qwen2.5 Coder 32B Instruct
BenchmarkR1 0528Qwen2.5 Coder 32B InstructLeader
MMLU Pro (Artificial Analysis run)84.9%63.5%R1 0528
MMLUNot measured79.1%Only Qwen2.5 Coder 32B Instruct measured
AI2 Reasoning ChallengeNot measured70.5%Only Qwen2.5 Coder 32B Instruct measured
LMArena Text: science14301221R1 0528
LMArena Text: medicine and healthcare14451187R1 0528
LMArena Text: legal and government14191257R1 0528
LMArena Text: business and finance14021224R1 0528
Neither model has a result on the other 10 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for R1 0528 and Qwen2.5 Coder 32B Instruct
BenchmarkR1 0528Qwen2.5 Coder 32B InstructLeader
Design Arena: websites1149Not measuredOnly R1 0528 measured
Design Arena: UI components1102Not measuredOnly R1 0528 measured
Design Arena: game dev1098Not measuredOnly R1 0528 measured
Design Arena: data viz1182Not measuredOnly R1 0528 measured
Design Arena: 3D1111Not measuredOnly R1 0528 measured
Design Arena: all code categories1139Not measuredOnly R1 0528 measured
Design Arena: SVG1038Not measuredOnly R1 0528 measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index110
General benchmarks for R1 0528 and Qwen2.5 Coder 32B Instruct
BenchmarkR1 0528Qwen2.5 Coder 32B InstructLeader
IFBench39.6%Not measuredOnly R1 0528 measured
Long context reasoning (AA-LCR)55.7%Not measuredOnly R1 0528 measured
Fiction.LiveBench75.0%Not measuredOnly R1 0528 measured
Creative writing (Lech Mazur)81.9%Not measuredOnly R1 0528 measured
HellaSwagNot measured83.0%Only Qwen2.5 Coder 32B Instruct measured
WinoGrandeNot measured80.8%Only Qwen2.5 Coder 32B Instruct measured
LMArena Text14281230R1 0528
LMArena Text: instruction following13821223R1 0528
LMArena Text: creative writing14051174R1 0528
LMArena Text: English14371248R1 0528
LMArena Text: non-English14121205R1 0528
LMArena Text: Chinese14421222R1 0528
LMArena Text: German1404Not measuredOnly R1 0528 measured
LMArena Text: Japanese1391Not measuredOnly R1 0528 measured
LMArena Text: Korean1360Not measuredOnly R1 0528 measured
LMArena Text: French1417Not measuredOnly R1 0528 measured
LMArena Text: Spanish1411Not measuredOnly R1 0528 measured
LMArena Text: Russian14231228R1 0528
LMArena Text: Polish1428Not measuredOnly R1 0528 measured
LMArena Text: multi-turn14051222R1 0528
LMArena Text: longer queries13911251R1 0528
LMArena Text: writing and language14021191R1 0528
LMArena Text: entertainment and media14001150R1 0528
Neither model has a result on the other 23 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for R1 0528 and Qwen2.5 Coder 32B Instruct
BenchmarkR1 0528Qwen2.5 Coder 32B InstructLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

R1 0528$0.0016Fits in one request
Qwen2.5 Coder 32B Instruct$0.0012Fits in one request

Qwen2.5 Coder 32B Instruct costs less

Repository review

50K input + 3K output tokens

R1 0528$0.031Fits in one request
Qwen2.5 Coder 32B Instruct$0.036Exceeds the context window

R1 0528 costs less

Agent loop

200K input + 10K output tokens

R1 0528$0.121Exceeds the context window
Qwen2.5 Coder 32B Instruct$0.142Exceeds the context window

R1 0528 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of R1 0528 and Qwen2.5 Coder 32B Instruct
SpecificationDeepSeek R1 0528Qwen2.5 Coder 32B Instruct
MakerDeepSeekQwen
WeightsOpen weightsOpen weights
ReleasedMay 28, 2025November 11, 2024
Context window164K33K
Input $/Mtok$0.50$0.66
Output $/Mtok$2.15$1.00
Coding index71.430.5
Independent measurements behind it12
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is R1 0528 better than Qwen2.5 Coder 32B Instruct for coding?

Pick R1 0528 for coding: it scores 71.4 on the Vibe Coding Index against 30.5 for Qwen2.5 Coder 32B Instruct, though on 1 benchmark against 2. Pick Qwen2.5 Coder 32B Instruct when output tokens cost 2.1x less.

Which is cheaper, R1 0528 or Qwen2.5 Coder 32B Instruct?

R1 0528 costs $0.50 per million input tokens and $2.15 per million output tokens; Qwen2.5 Coder 32B Instruct costs $0.66 and $1.00. Cost per solved task is known for neither of them.

Which has the bigger context window, R1 0528 or Qwen2.5 Coder 32B Instruct?

R1 0528, with 164K tokens against 33K.

How many benchmarks is the R1 0528 vs Qwen2.5 Coder 32B Instruct comparison based on?

28 benchmarks have a result for both models as of October 21, 2026. R1 0528's coding index rests on 1 independent benchmark and Qwen2.5 Coder 32B Instruct's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next