LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

R1 0528 vs Beam 1.0 501B A23B

Updated October 21, 2026. 25 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 Beam 1.0 501B A23B
R1 0528DeepSeek
Coding
71.4
Overall
13.1
Output $/M
$2.15
9
R Beam 1.0 501B A23BReflection
Coding
33.8
Overall
No data
Output $/M
$1.00
16
vs boards won of 25 shared

Decision reading

Pick R1 0528 for coding: it scores 71.4 on the Vibe Coding Index against 33.8 for Beam 1.0 501B A23B.

Pick Beam 1.0 501B A23B when output tokens cost 2.1x less, or when the context window is larger, 1.05M against 164K tokens.

Model AR1 0528DeepSeek71.4/1001 independent benchmarkNo cost per solved taskModel BBeam 1.0 501B A23BReflection33.8/1001 independent benchmarkNo cost per solved task
Shared results
25
R1 0528 only
34
Beam 1.0 501B A23B only
3
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, Beam 1.0 501B A23B 33.8 from 1 benchmark.
Widest category
Web design, 14.3 points apart on average over 2 shared benchmarks.
Widest single gap
Design Arena: game dev: R1 0528 1098 against Beam 1.0 501B A23B 1222, 15.5 points apart on a 0 to 100 scale.
Output price
R1 0528 $2.15 against Beam 1.0 501B A23B $1.00 per million output tokens, 2.1x apart.
Context window
R1 0528 takes 164K tokens, Beam 1.0 501B A23B 1.05M.

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 0528BarsBeam 1.0 501B A23BTies
Coding02
Reasoning03
Math02
Knowledge22
Web design02
General75
All shared boards916
CodingLike-for-likeFour of these boards feed the Vibe Coding Index02
Coding benchmarks for R1 0528 and Beam 1.0 501B A23B
BenchmarkR1 0528Beam 1.0 501B A23BLeader
Aider polyglot71.4%Not measuredOnly R1 0528 measured
LMArena WebDevNot measured1437Only Beam 1.0 501B A23B measured
LiveCodeBench (Artificial Analysis run)77.0%Not measuredOnly R1 0528 measured
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: coding14271473Beam 1.0 501B A23B
LMArena Text: software and IT14351461Beam 1.0 501B A23B
LMArena WebDev: ReactNot measured1443Only Beam 1.0 501B A23B measured
LMArena WebDev: HTMLNot measured1436Only Beam 1.0 501B A23B measured
Neither model has a result on the other 28 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Intelligence benchmarks for R1 0528 and Beam 1.0 501B A23B
BenchmarkR1 0528Beam 1.0 501B A23BLeader
AA Intelligence Index13.1Not measuredOnly R1 0528 measured
Neither model has a result on the other 1 board here
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
Agentic work benchmarks for R1 0528 and Beam 1.0 501B A23B
BenchmarkR1 0528Beam 1.0 501B A23BLeader
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 index03
Reasoning benchmarks for R1 0528 and Beam 1.0 501B A23B
BenchmarkR1 0528Beam 1.0 501B A23BLeader
GPQA Diamond (Artificial Analysis run)81.3%Not measuredOnly R1 0528 measured
Humanity's Last Exam (Artificial Analysis run)15.8%Not measuredOnly R1 0528 measured
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 prompts14151442Beam 1.0 501B A23B
LMArena Text: expert13941447Beam 1.0 501B A23B
LMArena Text: hard prompts in English14221451Beam 1.0 501B A23B
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for R1 0528 and Beam 1.0 501B A23B
BenchmarkR1 0528Beam 1.0 501B A23BLeader
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
LMArena Text: math14001459Beam 1.0 501B A23B
LMArena Text: mathematical work14151475Beam 1.0 501B A23B
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index22
Knowledge benchmarks for R1 0528 and Beam 1.0 501B A23B
BenchmarkR1 0528Beam 1.0 501B A23BLeader
MMLU Pro (Artificial Analysis run)84.9%Not measuredOnly R1 0528 measured
LMArena Text: science14301430R1 0528
LMArena Text: medicine and healthcare14451376R1 0528
LMArena Text: legal and government14191433Beam 1.0 501B A23B
LMArena Text: business and finance14021430Beam 1.0 501B A23B
Neither model has a result on the other 12 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index02
Web design benchmarks for R1 0528 and Beam 1.0 501B A23B
BenchmarkR1 0528Beam 1.0 501B A23BLeader
Design Arena: websites11491253Beam 1.0 501B A23B
Design Arena: UI components1102Not measuredOnly R1 0528 measured
Design Arena: game dev10981222Beam 1.0 501B A23B
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 index75
General benchmarks for R1 0528 and Beam 1.0 501B A23B
BenchmarkR1 0528Beam 1.0 501B A23BLeader
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
LMArena Text14281425R1 0528
LMArena Text: instruction following13821430Beam 1.0 501B A23B
LMArena Text: creative writing14051390R1 0528
LMArena Text: English14371436R1 0528
LMArena Text: non-English14121413Beam 1.0 501B A23B
LMArena Text: Chinese14421424R1 0528
LMArena Text: German1404Not measuredOnly R1 0528 measured
LMArena Text: Japanese1391Not measuredOnly R1 0528 measured
LMArena Text: Korean1360Not measuredOnly R1 0528 measured
LMArena Text: French14171461Beam 1.0 501B A23B
LMArena Text: Spanish1411Not measuredOnly R1 0528 measured
LMArena Text: Russian14231412R1 0528
LMArena Text: Polish1428Not measuredOnly R1 0528 measured
LMArena Text: multi-turn14051414Beam 1.0 501B A23B
LMArena Text: longer queries13911429Beam 1.0 501B A23B
LMArena Text: writing and language14021400R1 0528
LMArena Text: entertainment and media14001399R1 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 Beam 1.0 501B A23B
BenchmarkR1 0528Beam 1.0 501B A23BLeader
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
Beam 1.0 501B A23B$0.0008Fits in one request

Beam 1.0 501B A23B costs less

Repository review

50K input + 3K output tokens

R1 0528$0.031Fits in one request
Beam 1.0 501B A23B$0.018Fits in one request

Beam 1.0 501B A23B costs less

Agent loop

200K input + 10K output tokens

R1 0528$0.121Exceeds the context window
Beam 1.0 501B A23B$0.070Fits in one request

Beam 1.0 501B A23B 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 Beam 1.0 501B A23B
SpecificationDeepSeek R1 0528Reflection Beam 1.0 501B A23B
MakerDeepSeekReflection
WeightsOpen weightsOpen weights
ReleasedMay 28, 2025October 16, 2026
Context window164K1.05M
Input $/Mtok$0.50$0.30
Output $/Mtok$2.15$1.00
Coding index71.433.8
Independent measurements behind it11
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is R1 0528 better than Beam 1.0 501B A23B for coding?

Pick R1 0528 for coding: it scores 71.4 on the Vibe Coding Index against 33.8 for Beam 1.0 501B A23B. Pick Beam 1.0 501B A23B when output tokens cost 2.1x less, or when the context window is larger, 1.05M against 164K tokens.

Which is cheaper, R1 0528 or Beam 1.0 501B A23B?

R1 0528 costs $0.50 per million input tokens and $2.15 per million output tokens; Beam 1.0 501B A23B costs $0.30 and $1.00. Cost per solved task is known for neither of them.

Which has the bigger context window, R1 0528 or Beam 1.0 501B A23B?

Beam 1.0 501B A23B, with 1.05M tokens against 164K.

How many benchmarks is the R1 0528 vs Beam 1.0 501B A23B comparison based on?

25 benchmarks have a result for both models as of October 21, 2026. R1 0528's coding index rests on 1 independent benchmark and Beam 1.0 501B A23B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next