Enter opens the highlighted result. Esc closes.

R1 0528 vs Qwen3 30B A3B Instruct 2507

R1 0528 leads Qwen3 30B A3B Instruct 2507 on the Artificial Analysis Intelligence Index, 13.1 to 7.5, and Qwen3 30B A3B Instruct 2507 costs 7.3x less per output token ($0.30 vs $2.18 per million). Updated October 22, 2026; 41 benchmarks have a result for both.

Replace R1 0528 Replace Qwen3 30B A3B Instruct 2507
R1 0528DeepSeek
Coding
No data
Overall
46.8
Output $/M
$2.18
37
Qwen3 30B A3B Instruct 2507Qwen
Coding
No data
Overall
41.5
Output $/M
$0.30
4
vs boards won of 41 shared

R1 0528 or Qwen3 30B A3B Instruct 2507: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick R1 0528 for work measured by LMArena Text: expert or IFBench, where it leads.

Model AR1 0528DeepSeekNot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen3 30B A3B Instruct 2507QwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
41
R1 0528 only
22
Qwen3 30B A3B Instruct 2507 only
4
Like-for-like categories
7 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

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 not benchmarked, Qwen3 30B A3B Instruct 2507 not benchmarked.
Widest category
Agentic work, 8.5 points apart on average over 1 shared benchmark.
Widest single gap
GPQA Diamond (Epoch AI run): R1 0528 76.3% against Qwen3 30B A3B Instruct 2507 55.6%, 20.7 points apart on a 0 to 100 scale.
Output price
R1 0528 $2.18 against Qwen3 30B A3B Instruct 2507 $0.30 per million output tokens, 7.3x apart.
Context window
R1 0528 takes 164K tokens, Qwen3 30B A3B Instruct 2507 262K.

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 0528BarsQwen3 30B A3B Instruct 2507Ties
Coding40
Intelligence10
Agentic work10
Reasoning51
Math50
Knowledge50
General163
All shared boards374
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
Coding benchmarks for R1 0528 and Qwen3 30B A3B Instruct 2507
BenchmarkR1 0528Qwen3 30B A3B Instruct 2507Leader
Aider polyglot71.4%Not measuredOnly R1 0528 measured
LiveCodeBench (Artificial Analysis run)77.0%70.7%R1 0528
SciCodeNot measured33.0%Only Qwen3 30B A3B Instruct 2507 measured
Terminal-Bench Hard (Artificial Analysis run)15.9%6.1%R1 0528
WeirdML41.6%Not measuredOnly R1 0528 measured
ALE-Bench804.1Not measuredOnly R1 0528 measured
LMArena Text: coding14271416R1 0528
LMArena Text: software and IT14351417R1 0528
Neither model has a result on the other 35 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for R1 0528 and Qwen3 30B A3B Instruct 2507
BenchmarkR1 0528Qwen3 30B A3B Instruct 2507Leader
AA Intelligence Index13.17.5R1 0528
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for R1 0528 and Qwen3 30B A3B Instruct 2507
BenchmarkR1 0528Qwen3 30B A3B Instruct 2507Leader
τ²-Bench Telecom36.5%28.1%R1 0528
METR time horizons53.8%Not measuredOnly R1 0528 measured
DeepResearch Bench35.1%Not measuredOnly R1 0528 measured
Berkeley Function Calling Leaderboard (BFCL)Not measured41.4%Only Qwen3 30B A3B Instruct 2507 measured
BrowseComp-Plus16.4%Not measuredOnly R1 0528 measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index51
Reasoning benchmarks for R1 0528 and Qwen3 30B A3B Instruct 2507
BenchmarkR1 0528Qwen3 30B A3B Instruct 2507Leader
GPQA Diamond (Artificial Analysis run)81.3%70.7%R1 0528
Humanity's Last Exam (Artificial Analysis run)15.8%10.3%R1 0528
GPQA Diamond (Epoch AI run)76.3%55.6%R1 0528
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 prompts14151398R1 0528
LMArena Text: expert13941397Qwen3 30B A3B Instruct 2507
LMArena Text: hard prompts in English14221406R1 0528
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index50
Math benchmarks for R1 0528 and Qwen3 30B A3B Instruct 2507
BenchmarkR1 0528Qwen3 30B A3B Instruct 2507Leader
AA Math Index76.066.3R1 0528
AIME 2025 (Artificial Analysis run)76.0%66.3%R1 0528
OTIS Mock AIME66.4%62.2%R1 0528
MATH level 596.6%Not measuredOnly R1 0528 measured
LMArena Text: math14001394R1 0528
LMArena Text: mathematical work14151411R1 0528
MathArena12.9%Not measuredOnly R1 0528 measured
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for R1 0528 and Qwen3 30B A3B Instruct 2507
BenchmarkR1 0528Qwen3 30B A3B Instruct 2507Leader
MMLU Pro (Artificial Analysis run)84.9%80.5%R1 0528
LMArena Text: science14301393R1 0528
LMArena Text: medicine and healthcare14451392R1 0528
LMArena Text: legal and government14191387R1 0528
LMArena Text: business and finance14021389R1 0528
PRBench Finance32.7%Not measuredOnly R1 0528 measured
PRBench Legal36.6%Not measuredOnly R1 0528 measured
Neither model has a result on the other 13 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for R1 0528 and Qwen3 30B A3B Instruct 2507
BenchmarkR1 0528Qwen3 30B A3B Instruct 2507Leader
Design Arena: websites1149Not measuredOnly R1 0528 measured
Design Arena: UI components1100Not measuredOnly R1 0528 measured
Design Arena: game dev1097Not measuredOnly R1 0528 measured
Design Arena: data viz1182Not measuredOnly R1 0528 measured
Design Arena: 3D1110Not measuredOnly R1 0528 measured
Design Arena: all code categories1138Not 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 index163
General benchmarks for R1 0528 and Qwen3 30B A3B Instruct 2507
BenchmarkR1 0528Qwen3 30B A3B Instruct 2507Leader
IFBench39.6%50.7%Qwen3 30B A3B Instruct 2507
Long context reasoning (AA-LCR)55.7%61.3%Qwen3 30B A3B Instruct 2507
DTBenchNot measured67.2%Only Qwen3 30B A3B Instruct 2507 measured
LMCANot measured22.4%Only Qwen3 30B A3B Instruct 2507 measured
Fiction.LiveBench75.0%Not measuredOnly R1 0528 measured
Creative writing (Lech Mazur)81.9%Not measuredOnly R1 0528 measured
LMArena Text14281384R1 0528
LMArena Text: instruction following13821363R1 0528
LMArena Text: creative writing14051317R1 0528
LMArena Text: English14371391R1 0528
LMArena Text: non-English14121372R1 0528
LMArena Text: Chinese14421432R1 0528
LMArena Text: German14041379R1 0528
LMArena Text: Japanese13911337R1 0528
LMArena Text: Korean13601330R1 0528
LMArena Text: French14171419Qwen3 30B A3B Instruct 2507
LMArena Text: Spanish14111404R1 0528
LMArena Text: Russian14231369R1 0528
LMArena Text: Polish14281353R1 0528
LMArena Text: multi-turn14051378R1 0528
LMArena Text: longer queries13911378R1 0528
LMArena Text: writing and language14021336R1 0528
LMArena Text: entertainment and media14001334R1 0528
Neither model has a result on the other 25 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for R1 0528 and Qwen3 30B A3B Instruct 2507
BenchmarkR1 0528Qwen3 30B A3B Instruct 2507Leader
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
Qwen3 30B A3B Instruct 2507$0.0002Fits in one request

Qwen3 30B A3B Instruct 2507 costs less

Repository review

50K input + 3K output tokens

R1 0528$0.032Fits in one request
Qwen3 30B A3B Instruct 2507$0.0054Fits in one request

Qwen3 30B A3B Instruct 2507 costs less

Agent loop

200K input + 10K output tokens

R1 0528$0.122Exceeds the context window
Qwen3 30B A3B Instruct 2507$0.021Fits in one request

Qwen3 30B A3B Instruct 2507 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 Qwen3 30B A3B Instruct 2507
SpecificationDeepSeek R1 0528Qwen3 30B A3B Instruct 2507
MakerDeepSeekQwen
WeightsOpen weightsOpen weights
ReleasedMay 28, 2025July 29, 2025
Context window164K262K
Input $/Mtok$0.50$0.09
Output $/Mtok$2.18$0.30
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is R1 0528 better than Qwen3 30B A3B Instruct 2507 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick R1 0528 for work measured by LMArena Text: expert or IFBench, where it leads.

Which is cheaper, R1 0528 or Qwen3 30B A3B Instruct 2507?

R1 0528 costs $0.50 per million input tokens and $2.18 per million output tokens; Qwen3 30B A3B Instruct 2507 costs $0.09 and $0.30. Cost per solved task is known for neither of them.

Which has the bigger context window, R1 0528 or Qwen3 30B A3B Instruct 2507?

Qwen3 30B A3B Instruct 2507, with 262K tokens against 164K.

How many benchmarks is the R1 0528 vs Qwen3 30B A3B Instruct 2507 comparison based on?

41 benchmarks have a result for both models as of October 22, 2026. R1 0528's coding index rests on 0 independent benchmarks and Qwen3 30B A3B Instruct 2507's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next