Enter opens the highlighted result. Esc closes.

GPT-4 vs MiniMax M2

MiniMax M2 leads GPT-4 on the Artificial Analysis Intelligence Index, 18.6 to 6.7, and MiniMax M2 costs 58.8x less per output token ($1.02 vs $60.00 per million). Updated October 21, 2026; 31 benchmarks have a result for both.

Replace GPT-4 Replace MiniMax M2
GPT-4OpenAI
Coding
No data
Overall
No data
Output $/M
$60.00
0
MiniMax M2MiniMax
Coding
No data
Overall
No data
Output $/M
$1.02
31
vs boards won of 31 shared

GPT-4 or MiniMax M2: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick GPT-4 for work measured by SWE-bench Verified or LMArena Text: coding, where it leads.

Model AGPT-4OpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BMiniMax M2MiniMaxNot benchmarked1 independent benchmark$0.702 per solved task
Shared results
31
GPT-4 only
14
MiniMax M2 only
19
Like-for-like categories
6 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

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-4 not benchmarked, MiniMax M2 not benchmarked.
Widest category
Reasoning, 32.1 points apart on average over 4 shared benchmarks.
Widest single gap
GPQA Diamond (Artificial Analysis run): GPT-4 34.9% against MiniMax M2 77.7%, 42.8 points apart on a 0 to 100 scale.
Output price
GPT-4 $60.00 against MiniMax M2 $1.02 per million output tokens, 58.8x apart.
Context window
GPT-4 takes 8K tokens, MiniMax M2 205K.

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-4BarsMiniMax M2Ties
Coding03
Intelligence01
Reasoning04
Math02
Knowledge05
General016
All shared boards031
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for GPT-4 and MiniMax M2
BenchmarkGPT-4MiniMax M2Leader
SWE-bench Verified22.4%61.0%MiniMax M2
SWE-bench Lite39.7%Not measuredOnly GPT-4 measured
SWE-bench (full test set)12.5%Not measuredOnly GPT-4 measured
LMArena WebDevNot measured1297Only MiniMax M2 measured
AA Coding Index13.1Not measuredOnly GPT-4 measured
LiveCodeBench (Artificial Analysis run)Not measured82.6%Only MiniMax M2 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured25.8%Only MiniMax M2 measured
Terminal-BenchNot measured30.0%Only MiniMax M2 measured
LMArena Text: coding12091371MiniMax M2
LMArena Text: software and IT11951373MiniMax M2
LMArena WebDev: HTMLNot measured1306Only MiniMax M2 measured
Neither model has a result on the other 28 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for GPT-4 and MiniMax M2
BenchmarkGPT-4MiniMax M2Leader
AA Intelligence Index6.718.6MiniMax M2
Epoch Capabilities Index125.7Not measuredOnly GPT-4 measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Agentic work benchmarks for GPT-4 and MiniMax M2
BenchmarkGPT-4MiniMax M2Leader
τ²-Bench TelecomNot measured86.8%Only MiniMax M2 measured
Vending-Bench 2Not measured$161Only MiniMax M2 measured
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
Reasoning benchmarks for GPT-4 and MiniMax M2
BenchmarkGPT-4MiniMax M2Leader
GPQA Diamond (Artificial Analysis run)34.9%77.7%MiniMax M2
Humanity's Last Exam (Artificial Analysis run)Not measured13.7%Only MiniMax M2 measured
BIG-Bench Hard75.1%Not measuredOnly GPT-4 measured
LMArena Text: hard prompts12001357MiniMax M2
LMArena Text: expert11491338MiniMax M2
LMArena Text: hard prompts in English12091376MiniMax M2
Kagi LLM BenchmarkNot measured57.8%Only MiniMax M2 measured
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for GPT-4 and MiniMax M2
BenchmarkGPT-4MiniMax M2Leader
AA Math IndexNot measured78.3Only MiniMax M2 measured
AIME 2025 (Artificial Analysis run)Not measured78.3%Only MiniMax M2 measured
GSM8K92.0%Not measuredOnly GPT-4 measured
LMArena Text: math12301351MiniMax M2
LMArena Text: mathematical work12281368MiniMax M2
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for GPT-4 and MiniMax M2
BenchmarkGPT-4MiniMax M2Leader
MMLU Pro (Artificial Analysis run)56.2%82.0%MiniMax M2
MMLU86.4%Not measuredOnly GPT-4 measured
AI2 Reasoning Challenge96.3%Not measuredOnly GPT-4 measured
LMArena Text: science11771348MiniMax M2
LMArena Text: medicine and healthcare11451367MiniMax M2
LMArena Text: legal and government11911349MiniMax M2
LMArena Text: business and finance11451336MiniMax M2
Neither model has a result on the other 11 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for GPT-4 and MiniMax M2
BenchmarkGPT-4MiniMax M2Leader
Design Arena: websitesNot measured1143Only MiniMax M2 measured
Design Arena: UI componentsNot measured1136Only MiniMax M2 measured
Design Arena: game devNot measured1118Only MiniMax M2 measured
Design Arena: data vizNot measured1140Only MiniMax M2 measured
Design Arena: 3DNot measured1098Only MiniMax M2 measured
Design Arena: all code categoriesNot measured1135Only MiniMax M2 measured
Design Arena: SVGNot measured1100Only MiniMax M2 measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index016
General benchmarks for GPT-4 and MiniMax M2
BenchmarkGPT-4MiniMax M2Leader
IFBench33.2%72.3%MiniMax M2
Long context reasoning (AA-LCR)Not measured64.3%Only MiniMax M2 measured
DTBench62.7%Not measuredOnly GPT-4 measured
LMCA17.1%Not measuredOnly GPT-4 measured
HellaSwag95.3%Not measuredOnly GPT-4 measured
WinoGrande87.5%Not measuredOnly GPT-4 measured
LMArena Text12061340MiniMax M2
LMArena Text: instruction following12011329MiniMax M2
LMArena Text: creative writing11911286MiniMax M2
LMArena Text: English12201364MiniMax M2
LMArena Text: non-English11941313MiniMax M2
LMArena Text: Chinese11841366MiniMax M2
LMArena Text: German11981357MiniMax M2
LMArena Text: Japanese1137Not measuredOnly GPT-4 measured
LMArena Text: Korean1087Not measuredOnly GPT-4 measured
LMArena Text: French12201336MiniMax M2
LMArena Text: Spanish11971326MiniMax M2
LMArena Text: Russian11951330MiniMax M2
LMArena Text: Polish12651312MiniMax M2
LMArena Text: multi-turn12061361MiniMax M2
LMArena Text: longer queries11901331MiniMax M2
LMArena Text: writing and language12191295MiniMax M2
LMArena Text: entertainment and media11841298MiniMax M2
Neither model has a result on the other 23 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-4 and MiniMax M2
BenchmarkGPT-4MiniMax M2Leader
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-4$0.060Fits in one request
MiniMax M2$0.0008Fits in one request

MiniMax M2 costs less

Repository review

50K input + 3K output tokens

GPT-4$1.68Exceeds the context window
MiniMax M2$0.016Fits in one request

MiniMax M2 costs less

Agent loop

200K input + 10K output tokens

GPT-4$6.60Exceeds the context window
MiniMax M2$0.061Exceeds the context window

MiniMax M2 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-4 and MiniMax M2
SpecificationOpenAI GPT-4MiniMax M2
MakerOpenAIMiniMax
WeightsNo public weights listedOpen weights
ReleasedMay 28, 2023October 23, 2025
Context window8K205K
Input $/Mtok$30.00$0.255
Output $/Mtok$60.00$1.02
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved taskNot computable$0.702
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4 better than MiniMax M2 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4 for work measured by SWE-bench Verified or LMArena Text: coding, where it leads.

Which is cheaper, GPT-4 or MiniMax M2?

GPT-4 costs $30.00 per million input tokens and $60.00 per million output tokens; MiniMax M2 costs $0.255 and $1.02. Cost per solved task is known for MiniMax M2 only.

Which has the bigger context window, GPT-4 or MiniMax M2?

MiniMax M2, with 205K tokens against 8K.

How many benchmarks is the GPT-4 vs MiniMax M2 comparison based on?

31 benchmarks have a result for both models as of October 21, 2026. GPT-4's coding index rests on 0 independent benchmarks and MiniMax M2's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next