LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Grok 4.3 vs Mistral Medium 3.5

Updated October 21, 2026. 78 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Grok 4.3 Replace Mistral Medium 3.5
Grok 4.3xAI
Coding
22.5
Overall
24.9
Output $/M
$2.50
50
Mistral Medium 3.5Mistral AI
Coding
9.2
Overall
14.2
Output $/M
$7.50
28
vs boards won of 78 shared

Decision reading

Pick Grok 4.3 for coding: it scores 22.5 on the Vibe Coding Index against 9.2 for Mistral Medium 3.5.

Pick Mistral Medium 3.5 when what matters is AA Coding Index or LMArena Text: coding, where it leads.

Model AGrok 4.3xAI22.5/1001 independent benchmark$0.31 per solved taskModel BMistral Medium 3.5Mistral AI9.2/1001 independent benchmark$6.02 per solved task
Shared results
78
Grok 4.3 only
26
Mistral Medium 3.5 only
2
Like-for-like categories
8 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
Grok 4.3 22.5 from 1 benchmark, Mistral Medium 3.5 9.2 from 1 benchmark.
Widest category
Reasoning, 15.2 points apart on average over 8 shared benchmarks.
Widest single gap
GPQA Diamond: Grok 4.3 91.4% against Mistral Medium 3.5 34.9%, 56.6 points apart on a 0 to 100 scale.
Output price
Grok 4.3 $2.50 against Mistral Medium 3.5 $7.50 per million output tokens, 3.0x apart.
Context window
Grok 4.3 takes 1M tokens, Mistral Medium 3.5 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
CategoryGrok 4.3BarsMistral Medium 3.5Ties
Coding103
Intelligence10
Agentic work60
Reasoning44
Math12
Knowledge64
Web design80
General1415
All shared boards5028
CodingLike-for-likeFour of these boards feed the Vibe Coding Index103
Coding benchmarks for Grok 4.3 and Mistral Medium 3.5
BenchmarkGrok 4.3Mistral Medium 3.5Leader
LMArena WebDev13581264Grok 4.3
AA Coding Index42.246.9Mistral Medium 3.5
LiveCodeBench (Vals AI)84.5%Not measuredOnly Grok 4.3 measured
SWE-bench Verified (Vals AI)71.4%66.4%Grok 4.3
Vibe Code Bench (Vals AI)19.4%2.9%Grok 4.3
Code migration (Vals AI)6.8%5.1%Grok 4.3
ProgramBench (Vals AI)0.0%Not measuredOnly Grok 4.3 measured
Terminal-Bench 2.1 (Vals AI)42.0%39.0%Grok 4.3
SkillsBench (Vals AI)40.6%Not measuredOnly Grok 4.3 measured
SciCode48.3%40.2%Grok 4.3
Terminal-Bench Hard (Artificial Analysis run)37.9%33.3%Grok 4.3
WeirdML49.9%Not measuredOnly Grok 4.3 measured
ALE-Bench944.2764.0Grok 4.3
LMArena Text: coding14151460Mistral Medium 3.5
LMArena Text: software and IT14161458Mistral Medium 3.5
LMArena WebDev: React13531254Grok 4.3
LMArena WebDev: HTML13671308Grok 4.3
LMArena WebDev: from an image1375Not measuredOnly Grok 4.3 measured
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Grok 4.3 and Mistral Medium 3.5
BenchmarkGrok 4.3Mistral Medium 3.5Leader
AA Intelligence Index24.914.2Grok 4.3
Epoch Capabilities IndexNot measured141.4Only Mistral Medium 3.5 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index60
Agentic work benchmarks for Grok 4.3 and Mistral Medium 3.5
BenchmarkGrok 4.3Mistral Medium 3.5Leader
AA Agentic Index15.57.0Grok 4.3
Design Arena: agents building web apps1126Not measuredOnly Grok 4.3 measured
Design Arena: agents building full-stack apps1006Not measuredOnly Grok 4.3 measured
Design Arena: agents building mobile apps1059Not measuredOnly Grok 4.3 measured
Design Arena: agents building Android apps967Not measuredOnly Grok 4.3 measured
Design Arena: agents building Godot games914Not measuredOnly Grok 4.3 measured
Design Arena: agents building games1007Not measuredOnly Grok 4.3 measured
Design Arena: HTML slides1008Not measuredOnly Grok 4.3 measured
Design Arena: PowerPoint slides1012Not measuredOnly Grok 4.3 measured
Finance Agent (Vals AI)37.7%32.1%Grok 4.3
Tax Agent Bench (Vals AI)6.2%4.5%Grok 4.3
Legal Research Bench (Vals AI)15.4%9.1%Grok 4.3
Excel Modeling Benchmark (Vals AI)18.4%11.2%Grok 4.3
τ²-Bench Telecom97.7%94.2%Grok 4.3
Vending-Bench 2$35Not measuredOnly Grok 4.3 measured
LMArena Search1166Not measuredOnly Grok 4.3 measured
Neither model has a result on the other 23 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index44
Reasoning benchmarks for Grok 4.3 and Mistral Medium 3.5
BenchmarkGrok 4.3Mistral Medium 3.5Leader
GPQA Diamond91.4%34.9%Grok 4.3
MMMU Pro (Vals AI)83.1%Not measuredOnly Grok 4.3 measured
GPQA Diamond (Artificial Analysis run)90.1%74.8%Grok 4.3
Humanity's Last Exam (Artificial Analysis run)37.2%13.8%Grok 4.3
GPQA Diamond (Epoch AI run)88.8%Not measuredOnly Grok 4.3 measured
Chess puzzles18.0%Not measuredOnly Grok 4.3 measured
LMArena Text: hard prompts13961436Mistral Medium 3.5
LMArena Text: expert13841432Mistral Medium 3.5
LMArena Text: hard prompts in English14021445Mistral Medium 3.5
LMArena Vision: diagrams12411254Mistral Medium 3.5
LMArena Vision: homework12411230Grok 4.3
Neither model has a result on the other 10 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index12
Math benchmarks for Grok 4.3 and Mistral Medium 3.5
BenchmarkGrok 4.3Mistral Medium 3.5Leader
OTIS Mock AIME93.3%Not measuredOnly Grok 4.3 measured
FrontierMath, tiers 1 to 342.8%Not measuredOnly Grok 4.3 measured
FrontierMath, tier 414.6%Not measuredOnly Grok 4.3 measured
ProofBench11.0%9.0%Grok 4.3
LMArena Text: math13871431Mistral Medium 3.5
LMArena Text: mathematical work13961440Mistral Medium 3.5
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index64
Knowledge benchmarks for Grok 4.3 and Mistral Medium 3.5
BenchmarkGrok 4.3Mistral Medium 3.5Leader
MMLU Pro85.8%75.3%Grok 4.3
LegalBench (Vals AI)84.5%Not measuredOnly Grok 4.3 measured
CaseLaw (Vals AI)79.3%44.2%Grok 4.3
CorpFin (Vals AI)68.5%58.8%Grok 4.3
TaxEval (Vals AI)70.8%68.0%Grok 4.3
MortgageTax (Vals AI)48.3%28.9%Grok 4.3
MedCode (Vals AI)38.1%33.8%Grok 4.3
SimpleQA Verified33.2%Not measuredOnly Grok 4.3 measured
LMArena Text: science13991428Mistral Medium 3.5
LMArena Text: medicine and healthcare13841409Mistral Medium 3.5
LMArena Text: legal and government13861437Mistral Medium 3.5
LMArena Text: business and finance13811426Mistral Medium 3.5
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Grok 4.3 and Mistral Medium 3.5
BenchmarkGrok 4.3Mistral Medium 3.5Leader
Design Arena: websites11961142Grok 4.3
Design Arena: UI components11921079Grok 4.3
Design Arena: game dev11741079Grok 4.3
Design Arena: data viz11801120Grok 4.3
Design Arena: 3D11251061Grok 4.3
Design Arena: all code categories11871122Grok 4.3
Design Arena: SVG1081949Grok 4.3
Design Arena: ASCII art11251062Grok 4.3
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index1415
General benchmarks for Grok 4.3 and Mistral Medium 3.5
BenchmarkGrok 4.3Mistral Medium 3.5Leader
Public Benefits Bench (Vals AI)51.7%Not measuredOnly Grok 4.3 measured
SAGE (Vals AI)19.7%37.6%Mistral Medium 3.5
MedScribe (Vals AI)74.4%67.7%Grok 4.3
Vals Multimodal Index43.3%34.8%Grok 4.3
IFBench83.3%68.8%Grok 4.3
Long context reasoning (AA-LCR)75.0%69.3%Grok 4.3
DTBench90.7%75.5%Grok 4.3
LMCA38.3%26.1%Grok 4.3
Surface Evolver BenchNot measured26.9%Only Mistral Medium 3.5 measured
LMArena Text13971421Mistral Medium 3.5
LMArena Text: instruction following13661415Mistral Medium 3.5
LMArena Text: creative writing13801374Grok 4.3
LMArena Vision12291222Grok 4.3
LMArena Text: English14041433Mistral Medium 3.5
LMArena Text: non-English13851404Mistral Medium 3.5
LMArena Text: Chinese14221444Mistral Medium 3.5
LMArena Text: German13951453Mistral Medium 3.5
LMArena Text: Japanese1379Not measuredOnly Grok 4.3 measured
LMArena Text: Korean13541384Mistral Medium 3.5
LMArena Text: French14111448Mistral Medium 3.5
LMArena Text: Spanish13991411Mistral Medium 3.5
LMArena Text: Russian13991395Grok 4.3
LMArena Text: Polish13981430Mistral Medium 3.5
LMArena Text: multi-turn14061423Mistral Medium 3.5
LMArena Text: longer queries13931415Mistral Medium 3.5
LMArena Text: writing and language13851384Grok 4.3
LMArena Text: entertainment and media13701382Mistral Medium 3.5
LMArena Vision: English12351240Mistral Medium 3.5
LMArena Vision: Chinese12571244Grok 4.3
LMArena Vision: reading text12351233Grok 4.3
LMArena Vision: humor12221216Grok 4.3
LMArena Vision: recognizing things1217Not measuredOnly Grok 4.3 measured
LMArena Vision: creative writing12371198Grok 4.3
Neither model has a result on the other 13 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Grok 4.3 and Mistral Medium 3.5
BenchmarkGrok 4.3Mistral Medium 3.5Leader
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

Grok 4.3$0.0025Fits in one request
Mistral Medium 3.5$0.0053Fits in one request

Grok 4.3 costs less

Repository review

50K input + 3K output tokens

Grok 4.3$0.070Fits in one request
Mistral Medium 3.5$0.098Fits in one request

Grok 4.3 costs less

Agent loop

200K input + 10K output tokens

Grok 4.3$0.275Fits in one request
Mistral Medium 3.5$0.375Fits in one request

Grok 4.3 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 Grok 4.3 and Mistral Medium 3.5
SpecificationSpaceXAI Grok 4.3Mistral Medium 3.5
MakerxAIMistral AI
WeightsNo public weights listedNo public weights listed
ReleasedApril 30, 2026April 30, 2026
Context window1M262K
Input $/Mtok$1.25$1.50
Output $/Mtok$2.50$7.50
Coding index22.59.2
Independent measurements behind it11
Cost per solved task$0.31$6.02
SourceOpenRouter listingOpenRouter listing

Questions

Is Grok 4.3 better than Mistral Medium 3.5 for coding?

Pick Grok 4.3 for coding: it scores 22.5 on the Vibe Coding Index against 9.2 for Mistral Medium 3.5. Pick Mistral Medium 3.5 when what matters is AA Coding Index or LMArena Text: coding, where it leads.

Which is cheaper, Grok 4.3 or Mistral Medium 3.5?

Grok 4.3 costs $1.25 per million input tokens and $2.50 per million output tokens; Mistral Medium 3.5 costs $1.50 and $7.50. Per solved SWE-bench Verified task, Grok 4.3 costs $0.31 and Mistral Medium 3.5 $6.02.

Which has the bigger context window, Grok 4.3 or Mistral Medium 3.5?

Grok 4.3, with 1M tokens against 262K.

How many benchmarks is the Grok 4.3 vs Mistral Medium 3.5 comparison based on?

78 benchmarks have a result for both models as of October 21, 2026. Grok 4.3's coding index rests on 1 independent benchmark and Mistral Medium 3.5's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next