LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Mistral Large 4 vs Beam 1.0 501B A23B

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 Mistral Large 4 Replace Beam 1.0 501B A23B
Mistral Large 4Mistral AI
Coding
55.3
Overall
38.4
Output $/M
$4.18
18
R Beam 1.0 501B A23BReflection
Coding
33.8
Overall
No data
Output $/M
$1.00
10
vs boards won of 28 shared

Decision reading

Pick Mistral Large 4 for coding: it scores 55.3 on the Vibe Coding Index against 33.8 for Beam 1.0 501B A23B.

Pick Beam 1.0 501B A23B when output tokens cost 4.2x less, or when what matters is LMArena Text: expert or LMArena Text: hard prompts in English, where it leads.

Model AMistral Large 4Mistral AI55.3/1002 independent benchmarksNo cost per solved taskModel BBeam 1.0 501B A23BReflection33.8/1001 independent benchmarkNo cost per solved task
Shared results
28
Mistral Large 4 only
53
Beam 1.0 501B A23B only
0
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
Mistral Large 4 55.3 from 2 benchmarks, Beam 1.0 501B A23B 33.8 from 1 benchmark.
Widest category
Coding, 9.0 points apart on average over 5 shared benchmarks.
Widest single gap
LMArena WebDev: React: Mistral Large 4 1559 against Beam 1.0 501B A23B 1443, 19.3 points apart on a 0 to 100 scale.
Output price
Mistral Large 4 $4.18 against Beam 1.0 501B A23B $1.00 per million output tokens, 4.2x apart.
Context window
Both take 1.05M tokens.

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
CategoryMistral Large 4BarsBeam 1.0 501B A23BTies
Coding50
Reasoning12
Math11
Knowledge31
Web design20
General66
All shared boards1810
CodingLike-for-likeFour of these boards feed the Vibe Coding Index50
Coding benchmarks for Mistral Large 4 and Beam 1.0 501B A23B
BenchmarkMistral Large 4Beam 1.0 501B A23BLeader
LiveBench coding60.0%Not measuredOnly Mistral Large 4 measured
LMArena WebDev15431437Mistral Large 4
Terminal-Bench 4 (Vals AI)27.8%Not measuredOnly Mistral Large 4 measured
Vibe Code Bench (Vals AI)78.4%Not measuredOnly Mistral Large 4 measured
Code migration (Vals AI)30.6%Not measuredOnly Mistral Large 4 measured
IOI (Vals AI)45.3%Not measuredOnly Mistral Large 4 measured
SWE-bench Multimodal (Vals AI)33.1%Not measuredOnly Mistral Large 4 measured
Vibe Code Bench 1-100 (Vals AI)14.3%Not measuredOnly Mistral Large 4 measured
SciCode54.2%Not measuredOnly Mistral Large 4 measured
FrontierCode39.4%Not measuredOnly Mistral Large 4 measured
ALE-Bench1213.2Not measuredOnly Mistral Large 4 measured
LMArena Text: coding14781473Mistral Large 4
LMArena Text: software and IT14671461Mistral Large 4
LMArena WebDev: React15591443Mistral Large 4
LMArena WebDev: HTML14871436Mistral Large 4
Neither model has a result on the other 23 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Intelligence benchmarks for Mistral Large 4 and Beam 1.0 501B A23B
BenchmarkMistral Large 4Beam 1.0 501B A23BLeader
AA Intelligence Index38.4Not measuredOnly Mistral Large 4 measured
Epoch Capabilities Index150.0Not measuredOnly Mistral Large 4 measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Agentic work benchmarks for Mistral Large 4 and Beam 1.0 501B A23B
BenchmarkMistral Large 4Beam 1.0 501B A23BLeader
LiveBench research28.1%Not measuredOnly Mistral Large 4 measured
LiveBench browser8.0%Not measuredOnly Mistral Large 4 measured
LiveBench long agentic11.8%Not measuredOnly Mistral Large 4 measured
Finance Agent (Vals AI)54.7%Not measuredOnly Mistral Large 4 measured
Tax Agent Bench (Vals AI)30.4%Not measuredOnly Mistral Large 4 measured
Legal Research Bench (Vals AI)31.7%Not measuredOnly Mistral Large 4 measured
Harvey's Legal Agent Benchmark (Vals AI)17.5%Not measuredOnly Mistral Large 4 measured
Excel Modeling Benchmark (Vals AI)56.2%Not measuredOnly Mistral Large 4 measured
BioMysteryBench (Vals AI)67.0%Not measuredOnly Mistral Large 4 measured
Neither model has a result on the other 30 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index12
Reasoning benchmarks for Mistral Large 4 and Beam 1.0 501B A23B
BenchmarkMistral Large 4Beam 1.0 501B A23BLeader
LiveBench reasoning83.9%Not measuredOnly Mistral Large 4 measured
MysteryMechanism (Vals AI)12.2%Not measuredOnly Mistral Large 4 measured
Humanity's Last Exam (Artificial Analysis run)35.0%Not measuredOnly Mistral Large 4 measured
GPQA Diamond (Epoch AI run)88.1%Not measuredOnly Mistral Large 4 measured
Chess puzzles33.0%Not measuredOnly Mistral Large 4 measured
Mystery game puzzles17.0%Not measuredOnly Mistral Large 4 measured
LMArena Text: hard prompts14441442Mistral Large 4
LMArena Text: expert14441447Beam 1.0 501B A23B
LMArena Text: hard prompts in English14421451Beam 1.0 501B A23B
LMArena Vision: diagrams1288Not measuredOnly Mistral Large 4 measured
Neither model has a result on the other 11 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index11
Math benchmarks for Mistral Large 4 and Beam 1.0 501B A23B
BenchmarkMistral Large 4Beam 1.0 501B A23BLeader
OTIS Mock AIME98.3%Not measuredOnly Mistral Large 4 measured
FrontierMath, tiers 1 to 358.6%Not measuredOnly Mistral Large 4 measured
FrontierMath, tier 426.8%Not measuredOnly Mistral Large 4 measured
ProofBench10.0%Not measuredOnly Mistral Large 4 measured
LMArena Text: math14691459Mistral Large 4
LMArena Text: mathematical work14621475Beam 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 index31
Knowledge benchmarks for Mistral Large 4 and Beam 1.0 501B A23B
BenchmarkMistral Large 4Beam 1.0 501B A23BLeader
MedCode (Vals AI)40.7%Not measuredOnly Mistral Large 4 measured
SimpleQA Verified20.0%Not measuredOnly Mistral Large 4 measured
LMArena Text: science14481430Mistral Large 4
LMArena Text: medicine and healthcare14331376Mistral Large 4
LMArena Text: legal and government14251433Beam 1.0 501B A23B
LMArena Text: business and finance14391430Mistral Large 4
Neither model has a result on the other 11 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index20
Web design benchmarks for Mistral Large 4 and Beam 1.0 501B A23B
BenchmarkMistral Large 4Beam 1.0 501B A23BLeader
Design Arena: websites12581253Mistral Large 4
Design Arena: UI components1275Not measuredOnly Mistral Large 4 measured
Design Arena: game dev12261222Mistral Large 4
Design Arena: data viz1274Not measuredOnly Mistral Large 4 measured
Design Arena: 3D1253Not measuredOnly Mistral Large 4 measured
Design Arena: all code categories1259Not measuredOnly Mistral Large 4 measured
Design Arena: SVG1232Not measuredOnly Mistral Large 4 measured
Design Arena: ASCII art1203Not measuredOnly Mistral Large 4 measured
LiveBench design65.6%Not measuredOnly Mistral Large 4 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index66
General benchmarks for Mistral Large 4 and Beam 1.0 501B A23B
BenchmarkMistral Large 4Beam 1.0 501B A23BLeader
LiveBench data analysis76.5%Not measuredOnly Mistral Large 4 measured
MedScribe (Vals AI)80.4%Not measuredOnly Mistral Large 4 measured
Long context reasoning (AA-LCR)81.3%Not measuredOnly Mistral Large 4 measured
DTBench88.2%Not measuredOnly Mistral Large 4 measured
LMCA35.8%Not measuredOnly Mistral Large 4 measured
Surface Evolver Bench28.1%Not measuredOnly Mistral Large 4 measured
Furniture assembly20.8%Not measuredOnly Mistral Large 4 measured
LMArena Text14311425Mistral Large 4
LMArena Text: instruction following14221430Beam 1.0 501B A23B
LMArena Text: creative writing13631390Beam 1.0 501B A23B
LMArena Vision1272Not measuredOnly Mistral Large 4 measured
LMArena Text: English14331436Beam 1.0 501B A23B
LMArena Text: non-English14221413Mistral Large 4
LMArena Text: Chinese14921424Mistral Large 4
LMArena Text: Japanese1415Not measuredOnly Mistral Large 4 measured
LMArena Text: French14921461Mistral Large 4
LMArena Text: Spanish1455Not measuredOnly Mistral Large 4 measured
LMArena Text: Russian14171412Mistral Large 4
LMArena Text: multi-turn14351414Mistral Large 4
LMArena Text: longer queries14281429Beam 1.0 501B A23B
LMArena Text: writing and language13861400Beam 1.0 501B A23B
LMArena Text: entertainment and media13781399Beam 1.0 501B A23B
LMArena Vision: English1283Not measuredOnly Mistral Large 4 measured
LMArena Vision: reading text1284Not measuredOnly Mistral Large 4 measured
Neither model has a result on the other 22 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Mistral Large 4 and Beam 1.0 501B A23B
BenchmarkMistral Large 4Beam 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

Mistral Large 4$0.0034Fits 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

Mistral Large 4$0.081Fits 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

Mistral Large 4$0.314Fits in one request
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 Mistral Large 4 and Beam 1.0 501B A23B
SpecificationMistral Large 4Reflection Beam 1.0 501B A23B
MakerMistral AIReflection
WeightsNo public weights listedOpen weights
ReleasedOctober 6, 2026October 16, 2026
Context window1.05M1.05M
Input $/Mtok$1.36$0.30
Output $/Mtok$4.18$1.00
Coding index55.333.8
Independent measurements behind it21
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Mistral Large 4 better than Beam 1.0 501B A23B for coding?

Pick Mistral Large 4 for coding: it scores 55.3 on the Vibe Coding Index against 33.8 for Beam 1.0 501B A23B. Pick Beam 1.0 501B A23B when output tokens cost 4.2x less, or when what matters is LMArena Text: expert or LMArena Text: hard prompts in English, where it leads.

Which is cheaper, Mistral Large 4 or Beam 1.0 501B A23B?

Mistral Large 4 costs $1.36 per million input tokens and $4.18 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, Mistral Large 4 or Beam 1.0 501B A23B?

Neither: both take 1.05M tokens.

How many benchmarks is the Mistral Large 4 vs Beam 1.0 501B A23B comparison based on?

28 benchmarks have a result for both models as of October 21, 2026. Mistral Large 4's coding index rests on 2 independent benchmarks 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