LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Grok 4.7 vs Mistral Medium 3.5

Updated October 21, 2026. 61 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Grok 4.7 Replace Mistral Medium 3.5
Grok 4.7xAI
Coding
75.0
Overall
46.4
Output $/M
$6.00
39
Mistral Medium 3.5Mistral AI
Coding
9.2
Overall
14.2
Output $/M
$7.50
22
vs boards won of 61 shared

Decision reading

Pick Grok 4.7 for coding: it scores 75.0 on the Vibe Coding Index against 9.2 for Mistral Medium 3.5.

Pick Mistral Medium 3.5 when what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.

Model AGrok 4.7xAI75.0/1002 independent benchmarksNo cost per solved taskModel BMistral Medium 3.5Mistral AI9.2/1001 independent benchmark$6.02 per solved task
Shared results
61
Grok 4.7 only
38
Mistral Medium 3.5 only
19
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 4.7 75.0 from 2 benchmarks, Mistral Medium 3.5 9.2 from 1 benchmark.
Widest category
Coding, 38.4 points apart on average over 9 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Grok 4.7 86.2% against Mistral Medium 3.5 2.9%, 83.3 points apart on a 0 to 100 scale.
Output price
Grok 4.7 $6.00 against Mistral Medium 3.5 $7.50 per million output tokens, 1.3x apart.
Context window
Grok 4.7 takes 500K 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 4.7BarsMistral Medium 3.5Ties
Coding72
Intelligence20
Agentic work40
Reasoning42
Math12
Knowledge14
Web design60
General1412
All shared boards3922
CodingLike-for-likeFour of these boards feed the Vibe Coding Index72
Coding benchmarks for Grok 4.7 and Mistral Medium 3.5
BenchmarkGrok 4.7Mistral Medium 3.5Leader
LiveBench coding84.5%Not measuredOnly Grok 4.7 measured
LMArena WebDev16371264Grok 4.7
AA Coding IndexNot measured46.9Only Mistral Medium 3.5 measured
SWE-bench Verified (Vals AI)Not measured66.4%Only Mistral Medium 3.5 measured
Terminal-Bench 4 (Vals AI)28.8%Not measuredOnly Grok 4.7 measured
Vibe Code Bench (Vals AI)86.2%2.9%Grok 4.7
Code migration (Vals AI)44.8%5.1%Grok 4.7
ProgramBench (Vals AI)0.5%Not measuredOnly Grok 4.7 measured
IOI (Vals AI)57.7%Not measuredOnly Grok 4.7 measured
Terminal-Bench 2.1 (Vals AI)73.4%39.0%Grok 4.7
SWE-bench Multimodal (Vals AI)42.9%Not measuredOnly Grok 4.7 measured
CyberBench (Vals AI)69.5%Not measuredOnly Grok 4.7 measured
SciCode57.8%40.2%Grok 4.7
Terminal-Bench Hard (Artificial Analysis run)Not measured33.3%Only Mistral Medium 3.5 measured
FrontierCode47.6%Not measuredOnly Grok 4.7 measured
FrontierSWE29.5%Not measuredOnly Grok 4.7 measured
ALE-BenchNot measured764.0Only Mistral Medium 3.5 measured
LMArena Text: coding14321460Mistral Medium 3.5
LMArena Text: software and IT14211458Mistral Medium 3.5
LMArena WebDev: React16631254Grok 4.7
LMArena WebDev: HTML16271308Grok 4.7
LMArena WebDev: from an image1586Not measuredOnly Grok 4.7 measured
Neither model has a result on the other 16 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Grok 4.7 and Mistral Medium 3.5
BenchmarkGrok 4.7Mistral Medium 3.5Leader
AA Intelligence Index46.414.2Grok 4.7
Epoch Capabilities Index154.4141.4Grok 4.7
Agentic workLike-for-likePublic boards, shown as published, kept out of the index40
Agentic work benchmarks for Grok 4.7 and Mistral Medium 3.5
BenchmarkGrok 4.7Mistral Medium 3.5Leader
AA Agentic IndexNot measured7.0Only Mistral Medium 3.5 measured
LiveBench research86.4%Not measuredOnly Grok 4.7 measured
LiveBench browser60.0%Not measuredOnly Grok 4.7 measured
LiveBench long agentic50.1%Not measuredOnly Grok 4.7 measured
SREBench (Vals AI)3.8%Not measuredOnly Grok 4.7 measured
Finance Agent (Vals AI)52.3%32.1%Grok 4.7
Tax Agent Bench (Vals AI)34.2%4.5%Grok 4.7
Legal Research Bench (Vals AI)47.1%9.1%Grok 4.7
Harvey's Legal Agent Benchmark (Vals AI)18.3%Not measuredOnly Grok 4.7 measured
Excel Modeling Benchmark (Vals AI)67.0%11.2%Grok 4.7
BioMysteryBench (Vals AI)69.3%Not measuredOnly Grok 4.7 measured
Terminal-Bench-Science (Vals AI)10.0%Not measuredOnly Grok 4.7 measured
Vals Science Index34.8%Not measuredOnly Grok 4.7 measured
Robo-bench (Vals AI)0.2%Not measuredOnly Grok 4.7 measured
τ²-Bench TelecomNot measured94.2%Only Mistral Medium 3.5 measured
APEX-Agents54.6%Not measuredOnly Grok 4.7 measured
Vending-Bench 2$10,537Not measuredOnly Grok 4.7 measured
Neither model has a result on the other 22 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index42
Reasoning benchmarks for Grok 4.7 and Mistral Medium 3.5
BenchmarkGrok 4.7Mistral Medium 3.5Leader
GPQA DiamondNot measured34.9%Only Mistral Medium 3.5 measured
LiveBench reasoning82.7%Not measuredOnly Grok 4.7 measured
MysteryMechanism (Vals AI)25.2%Not measuredOnly Grok 4.7 measured
GPQA Diamond (Artificial Analysis run)Not measured74.8%Only Mistral Medium 3.5 measured
Humanity's Last Exam (Artificial Analysis run)43.1%13.8%Grok 4.7
GPQA Diamond (Epoch AI run)92.7%Not measuredOnly Grok 4.7 measured
ARC-AGI90.2%Not measuredOnly Grok 4.7 measured
ARC-AGI-261.4%Not measuredOnly Grok 4.7 measured
Chess puzzles41.0%Not measuredOnly Grok 4.7 measured
Mystery game puzzles29.0%Not measuredOnly Grok 4.7 measured
LMArena Text: hard prompts14151436Mistral Medium 3.5
LMArena Text: expert14391432Grok 4.7
LMArena Text: hard prompts in English14271445Mistral Medium 3.5
LMArena Vision: diagrams12541254Grok 4.7
LMArena Vision: homework13091230Grok 4.7
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index12
Math benchmarks for Grok 4.7 and Mistral Medium 3.5
BenchmarkGrok 4.7Mistral Medium 3.5Leader
OTIS Mock AIME98.1%Not measuredOnly Grok 4.7 measured
FrontierMath, tiers 1 to 353.0%Not measuredOnly Grok 4.7 measured
FrontierMath, tier 417.1%Not measuredOnly Grok 4.7 measured
ProofBench26.0%9.0%Grok 4.7
LMArena Text: math14141431Mistral Medium 3.5
LMArena Text: mathematical work14351440Mistral 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 index14
Knowledge benchmarks for Grok 4.7 and Mistral Medium 3.5
BenchmarkGrok 4.7Mistral Medium 3.5Leader
MMLU ProNot measured75.3%Only Mistral Medium 3.5 measured
LegalBench (Vals AI)84.4%Not measuredOnly Grok 4.7 measured
CaseLaw (Vals AI)Not measured44.2%Only Mistral Medium 3.5 measured
CorpFin (Vals AI)Not measured58.8%Only Mistral Medium 3.5 measured
TaxEval (Vals AI)Not measured68.0%Only Mistral Medium 3.5 measured
MortgageTax (Vals AI)Not measured28.9%Only Mistral Medium 3.5 measured
MedCode (Vals AI)49.5%33.8%Grok 4.7
SimpleQA Verified56.0%Not measuredOnly Grok 4.7 measured
LMArena Text: science14191428Mistral Medium 3.5
LMArena Text: medicine and healthcare13951409Mistral Medium 3.5
LMArena Text: legal and government14231437Mistral Medium 3.5
LMArena Text: business and finance13891426Mistral 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 index60
Web design benchmarks for Grok 4.7 and Mistral Medium 3.5
BenchmarkGrok 4.7Mistral Medium 3.5Leader
Design Arena: websites12551142Grok 4.7
Design Arena: UI components12711079Grok 4.7
Design Arena: game dev13141079Grok 4.7
Design Arena: data viz12271120Grok 4.7
Design Arena: 3D12691061Grok 4.7
Design Arena: all code categories12711122Grok 4.7
Design Arena: SVGNot measured949Only Mistral Medium 3.5 measured
Design Arena: ASCII artNot measured1062Only Mistral Medium 3.5 measured
LiveBench design78.0%Not measuredOnly Grok 4.7 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index1412
General benchmarks for Grok 4.7 and Mistral Medium 3.5
BenchmarkGrok 4.7Mistral Medium 3.5Leader
Vals Index58.6%Not measuredOnly Grok 4.7 measured
LiveBench data analysis76.9%Not measuredOnly Grok 4.7 measured
Public Benefits Bench (Vals AI)65.6%Not measuredOnly Grok 4.7 measured
SAGE (Vals AI)40.8%37.6%Grok 4.7
MedScribe (Vals AI)89.4%67.7%Grok 4.7
Vals Multimodal IndexNot measured34.8%Only Mistral Medium 3.5 measured
IFBenchNot measured68.8%Only Mistral Medium 3.5 measured
Long context reasoning (AA-LCR)80.0%69.3%Grok 4.7
DTBench96.0%75.5%Grok 4.7
LMCA49.4%26.1%Grok 4.7
Surface Evolver BenchNot measured26.9%Only Mistral Medium 3.5 measured
Furniture assembly20.8%Not measuredOnly Grok 4.7 measured
LMArena Text13991421Mistral Medium 3.5
LMArena Text: instruction following14061415Mistral Medium 3.5
LMArena Text: creative writing13811374Grok 4.7
LMArena Vision12311222Grok 4.7
LMArena Text: English14111433Mistral Medium 3.5
LMArena Text: non-English13861404Mistral Medium 3.5
LMArena Text: Chinese14491444Grok 4.7
LMArena Text: German13661453Mistral Medium 3.5
LMArena Text: Japanese1359Not measuredOnly Grok 4.7 measured
LMArena Text: Korean13831384Mistral Medium 3.5
LMArena Text: French14311448Mistral Medium 3.5
LMArena Text: Spanish14061411Mistral Medium 3.5
LMArena Text: Russian13991395Grok 4.7
LMArena Text: Polish14201430Mistral Medium 3.5
LMArena Text: multi-turn13941423Mistral Medium 3.5
LMArena Text: longer queries14161415Grok 4.7
LMArena Text: writing and language13941384Grok 4.7
LMArena Text: entertainment and media13761382Mistral Medium 3.5
LMArena Vision: English12291240Mistral Medium 3.5
LMArena Vision: Chinese12501244Grok 4.7
LMArena Vision: reading text12411233Grok 4.7
LMArena Vision: humorNot measured1216Only Mistral Medium 3.5 measured
LMArena Vision: creative writing12171198Grok 4.7
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Grok 4.7 and Mistral Medium 3.5
BenchmarkGrok 4.7Mistral 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 4.7$0.0050Fits in one request
Mistral Medium 3.5$0.0053Fits in one request

Grok 4.7 costs less

Repository review

50K input + 3K output tokens

Grok 4.7$0.118Fits in one request
Mistral Medium 3.5$0.098Fits in one request

Mistral Medium 3.5 costs less

Agent loop

200K input + 10K output tokens

Grok 4.7$0.460Fits in one request
Mistral Medium 3.5$0.375Fits in one request

Mistral Medium 3.5 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 4.7 and Mistral Medium 3.5
SpecificationSpaceXAI Grok 4.7Mistral Medium 3.5
MakerxAIMistral AI
WeightsNo public weights listedNo public weights listed
ReleasedSeptember 21, 2026April 30, 2026
Context window500K262K
Input $/Mtok$2.00$1.50
Output $/Mtok$6.00$7.50
Coding index75.09.2
Independent measurements behind it21
Cost per solved taskNot computable$6.02
SourceOpenRouter listingOpenRouter listing

Questions

Is Grok 4.7 better than Mistral Medium 3.5 for coding?

Pick Grok 4.7 for coding: it scores 75.0 on the Vibe Coding Index against 9.2 for Mistral Medium 3.5. Pick Mistral Medium 3.5 when what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, Grok 4.7 or Mistral Medium 3.5?

Grok 4.7 costs $2.00 per million input tokens and $6.00 per million output tokens; Mistral Medium 3.5 costs $1.50 and $7.50. Cost per solved task is known for Mistral Medium 3.5 only.

Which has the bigger context window, Grok 4.7 or Mistral Medium 3.5?

Grok 4.7, with 500K tokens against 262K.

How many benchmarks is the Grok 4.7 vs Mistral Medium 3.5 comparison based on?

61 benchmarks have a result for both models as of October 21, 2026. Grok 4.7's coding index rests on 2 independent benchmarks 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