Enter opens the highlighted result. Esc closes.

GPT-4o-mini vs Grok 4.20

Updated October 21, 2026. 17 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GPT-4o-mini Replace Grok 4.20
GPT-4o-miniOpenAI
Coding
No data
Overall
6.7
Output $/M
$0.60
1
Grok 4.20xAI
Coding
33.3
Overall
25.7
Output $/M
$2.50
16
vs boards won of 17 shared

Decision reading

Only Grok 4.20 has a coding score, 33.3 on the Vibe Coding Index; GPT-4o-mini has none, so the two cannot be ranked on coding.

GPT-4o-mini has the edge where output tokens cost 4.2x less, and where the benchmark that matters is MortgageTax (Vals AI), where it leads.

Model AGPT-4o-miniOpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BGrok 4.20xAI33.3/1002 independent benchmarks$0.72 per solved task
Shared results
17
GPT-4o-mini only
10
Grok 4.20 only
37
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
GPT-4o-mini not benchmarked, Grok 4.20 33.3 from 2 benchmarks.
Widest category
Math, 85.0 points apart on average over 1 shared benchmark.
Widest single gap
AIME: GPT-4o-mini 11.5% against Grok 4.20 96.5%, 85.0 points apart on a 0 to 100 scale.
Output price
GPT-4o-mini $0.60 against Grok 4.20 $2.50 per million output tokens, 4.2x apart.
Context window
GPT-4o-mini takes 128K tokens, Grok 4.20 2M.

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
CategoryGPT-4o-miniBarsGrok 4.20Ties
Coding01
Intelligence02
Reasoning05
Math01
Knowledge14
General03
All shared boards116
CodingLike-for-likeSix of these boards feed the Vibe Coding Index01
Coding benchmarks for GPT-4o-mini and Grok 4.20
BenchmarkGPT-4o-miniGrok 4.20Leader
AA Coding Index11.4Not measuredOnly GPT-4o-mini measured
LiveCodeBench (Vals AI)26.4%84.3%Grok 4.20
SWE-bench Verified (Vals AI)Not measured72.2%Only Grok 4.20 measured
Vibe Code Bench (Vals AI)Not measured4.1%Only Grok 4.20 measured
Code migration (Vals AI)Not measured0.3%Only Grok 4.20 measured
Terminal-Bench 2.1 (Vals AI)Not measured44.2%Only Grok 4.20 measured
LiveCodeBench (Artificial Analysis run)23.4%Not measuredOnly GPT-4o-mini measured
Terminal-Bench Hard (Artificial Analysis run)Not measured37.9%Only Grok 4.20 measured
Terminal-BenchNot measured57.3%Only Grok 4.20 measured
WeirdMLNot measured52.3%Only Grok 4.20 measured
Neither model has a result on the other 28 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-4o-mini and Grok 4.20
BenchmarkGPT-4o-miniGrok 4.20Leader
AA Intelligence Index6.725.7Grok 4.20
Epoch Capabilities Index126.5152.1Grok 4.20
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index12 boards, none shared
Agentic work benchmarks for GPT-4o-mini and Grok 4.20
BenchmarkGPT-4o-miniGrok 4.20Leader
Design Arena: agents building web appsNot measured1144Only Grok 4.20 measured
Design Arena: agents building full-stack appsNot measured1054Only Grok 4.20 measured
Design Arena: agents building mobile appsNot measured1090Only Grok 4.20 measured
Design Arena: agents building Android appsNot measured1052Only Grok 4.20 measured
Design Arena: agents building Godot gamesNot measured1089Only Grok 4.20 measured
Design Arena: HTML slidesNot measured1180Only Grok 4.20 measured
Finance Agent (Vals AI)Not measured28.5%Only Grok 4.20 measured
Tax Agent Bench (Vals AI)Not measured7.0%Only Grok 4.20 measured
Legal Research Bench (Vals AI)Not measured13.9%Only Grok 4.20 measured
Excel Modeling Benchmark (Vals AI)Not measured11.7%Only Grok 4.20 measured
τ²-Bench TelecomNot measured93.0%Only Grok 4.20 measured
Vending-Bench 2Not measured$4,663Only Grok 4.20 measured
Neither model has a result on the other 27 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for GPT-4o-mini and Grok 4.20
BenchmarkGPT-4o-miniGrok 4.20Leader
GPQA Diamond44.2%88.6%Grok 4.20
MMMU Pro (Vals AI)56.6%83.5%Grok 4.20
GPQA Diamond (Artificial Analysis run)42.6%91.1%Grok 4.20
Humanity's Last Exam (Artificial Analysis run)4.2%34.5%Grok 4.20
ARC-AGINot measured89.5%Only Grok 4.20 measured
ARC-AGI-20.0%65.1%Grok 4.20
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index01
Math benchmarks for GPT-4o-mini and Grok 4.20
BenchmarkGPT-4o-miniGrok 4.20Leader
AIME11.5%96.5%Grok 4.20
MATH 500 (Vals AI)72.6%Not measuredOnly GPT-4o-mini measured
MGSM (Vals AI)86.2%Not measuredOnly GPT-4o-mini measured
AA Math Index14.7Not measuredOnly GPT-4o-mini measured
AIME 2025 (Artificial Analysis run)14.7%Not measuredOnly GPT-4o-mini measured
GSM8K91.3%Not measuredOnly GPT-4o-mini measured
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 GPT-4o-mini and Grok 4.20
BenchmarkGPT-4o-miniGrok 4.20Leader
MMLU Pro62.7%86.3%Grok 4.20
LegalBench (Vals AI)Not measured77.7%Only Grok 4.20 measured
CaseLaw (Vals AI)Not measured54.4%Only Grok 4.20 measured
CorpFin (Vals AI)45.5%63.7%Grok 4.20
TaxEval (Vals AI)60.5%74.1%Grok 4.20
MortgageTax (Vals AI)54.5%45.4%GPT-4o-mini
MedQA (Vals AI)72.4%94.5%Grok 4.20
MedCode (Vals AI)Not measured32.2%Only Grok 4.20 measured
MMLU Pro (Artificial Analysis run)64.8%Not measuredOnly GPT-4o-mini measured
MMLU81.8%Not measuredOnly GPT-4o-mini measured
Neither model has a result on the other 7 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for GPT-4o-mini and Grok 4.20
BenchmarkGPT-4o-miniGrok 4.20Leader
Design Arena: websitesNot measured1229Only Grok 4.20 measured
Design Arena: UI componentsNot measured1199Only Grok 4.20 measured
Design Arena: game devNot measured1192Only Grok 4.20 measured
Design Arena: data vizNot measured1217Only Grok 4.20 measured
Design Arena: 3DNot measured1193Only Grok 4.20 measured
Design Arena: all code categoriesNot measured1221Only Grok 4.20 measured
Design Arena: SVGNot measured1164Only Grok 4.20 measured
Design Arena: ASCII artNot measured1174Only Grok 4.20 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index03
General benchmarks for GPT-4o-mini and Grok 4.20
BenchmarkGPT-4o-miniGrok 4.20Leader
SAGE (Vals AI)Not measured38.2%Only Grok 4.20 measured
MedScribe (Vals AI)Not measured63.4%Only Grok 4.20 measured
Vals Multimodal IndexNot measured39.1%Only Grok 4.20 measured
IFBench31.0%81.2%Grok 4.20
Long context reasoning (AA-LCR)Not measured69.0%Only Grok 4.20 measured
DTBench54.4%90.1%Grok 4.20
LMCA10.4%38.7%Grok 4.20
CL-benchNot measured22.2%Only Grok 4.20 measured
PIQA88.7%Not measuredOnly GPT-4o-mini measured
CL-bench LifeNot measured11.9%Only Grok 4.20 measured
Neither model has a result on the other 36 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-4o-mini and Grok 4.20
BenchmarkGPT-4o-miniGrok 4.20Leader
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

GPT-4o-mini$0.0004Fits in one request
Grok 4.20$0.0025Fits in one request

GPT-4o-mini costs less

Repository review

50K input + 3K output tokens

GPT-4o-mini$0.0093Fits in one request
Grok 4.20$0.070Fits in one request

GPT-4o-mini costs less

Agent loop

200K input + 10K output tokens

GPT-4o-mini$0.036Exceeds the context window
Grok 4.20$0.275Fits in one request

GPT-4o-mini 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 GPT-4o-mini and Grok 4.20
SpecificationOpenAI GPT-4o-miniSpaceXAI Grok 4.20
MakerOpenAIxAI
WeightsNo public weights listedNo public weights listed
ReleasedJuly 18, 2024March 31, 2026
Context window128K2M
Input $/Mtok$0.15$1.25
Output $/Mtok$0.60$2.50
Coding indexNot benchmarked33.3
Independent measurements behind it02
Cost per solved taskNot computable$0.72
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4o-mini better than Grok 4.20 for coding?

Only Grok 4.20 has a coding score, 33.3 on the Vibe Coding Index; GPT-4o-mini has none, so the two cannot be ranked on coding. GPT-4o-mini has the edge where output tokens cost 4.2x less, and where the benchmark that matters is MortgageTax (Vals AI), where it leads.

Which is cheaper, GPT-4o-mini or Grok 4.20?

GPT-4o-mini costs $0.15 per million input tokens and $0.60 per million output tokens; Grok 4.20 costs $1.25 and $2.50. Cost per solved task is known for Grok 4.20 only.

Which has the bigger context window, GPT-4o-mini or Grok 4.20?

Grok 4.20, with 2M tokens against 128K.

How many benchmarks is the GPT-4o-mini vs Grok 4.20 comparison based on?

17 benchmarks have a result for both models as of October 21, 2026. GPT-4o-mini's coding index rests on 0 independent benchmarks and Grok 4.20's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next