Enter opens the highlighted result. Esc closes.

GPT-6.1 Terra vs MiniMax M3

GPT-6.1 Terra leads MiniMax M3 on coding, 77.4 to 33.6 on the Vibe Coding Index, and MiniMax M3 costs 4.2x less per output token ($1.20 vs $5.00 per million). Updated October 29, 2026; 20 benchmarks have a result for both.

Replace GPT-6.1 Terra Replace MiniMax M3
GPT-6.1 TerraOpenAI
Coding
77.4
Overall
76.8
Output $/M
$5.00
17
MiniMax M3MiniMax
Coding
33.6
Overall
47.2
Output $/M
$1.20
3
vs boards won of 20 shared

GPT-6.1 Terra or MiniMax M3: which to pick

Pick GPT-6.1 Terra for coding: it scores 77.4 on the Vibe Coding Index against 33.6 for MiniMax M3, though on 4 benchmarks against 5.

Pick MiniMax M3 for output tokens 4.2x cheaper ($1.20 vs $5.00 per million) and work measured by Tax Agent Bench (Vals AI) or Legal Research Bench (Vals AI), where it leads.

Model AGPT-6.1 TerraOpenAI77.4/1004 independent benchmarksNo cost per solved taskModel BMiniMax M3MiniMax33.6/1005 independent benchmarks$0.56 per solved task
Shared results
20
GPT-6.1 Terra only
16
MiniMax M3 only
90
Like-for-like categories
7 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-6.1 Terra 77.4 from 4 benchmarks, MiniMax M3 33.6 from 5 benchmarks.
Widest category
Coding, 35.2 points apart on average over 7 shared benchmarks.
Widest single gap
Mystery game puzzles: GPT-6.1 Terra 74.0% against MiniMax M3 8.0%, 66.0 points apart on a 0 to 100 scale.
Output price
GPT-6.1 Terra $5.00 against MiniMax M3 $1.20 per million output tokens, 4.2x apart.
Context window
GPT-6.1 Terra takes 1.05M tokens, MiniMax M3 1.05M.

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-6.1 TerraBarsMiniMax M3Ties
Coding70
Intelligence10
Agentic work12
Reasoning30
Math10
Web design40
General01
All shared boards173
CodingLike-for-likeSix of these boards feed the Vibe Coding Index70
Coding benchmarks for GPT-6.1 Terra and MiniMax M3
BenchmarkGPT-6.1 TerraMiniMax M3Leader
LiveBench coding94.3%Not measuredOnly GPT-6.1 Terra measured
LMArena WebDev16731483GPT-6.1 Terra
AA Coding IndexNot measured58.6Only MiniMax M3 measured
LiveCodeBench (Vals AI)Not measured82.2%Only MiniMax M3 measured
SWE-bench Verified (Vals AI)Not measured75.0%Only MiniMax M3 measured
Terminal-Bench 4 (Vals AI)49.5%1.0%GPT-6.1 Terra
Vibe Code Bench (Vals AI)84.0%47.6%GPT-6.1 Terra
Code migration (Vals AI)Not measured19.9%Only MiniMax M3 measured
Terminal-Bench 2.1 (Vals AI)Not measured53.6%Only MiniMax M3 measured
SWE-bench Multimodal (Vals AI)Not measured33.3%Only MiniMax M3 measured
Vibe Code Bench 1-100 (Vals AI)Not measured9.2%Only MiniMax M3 measured
SkillsBench (Vals AI)Not measured51.5%Only MiniMax M3 measured
CyberBench (Vals AI)Not measured65.0%Only MiniMax M3 measured
SciCode55.1%47.1%GPT-6.1 Terra
Terminal-Bench Hard (Artificial Analysis run)Not measured42.4%Only MiniMax M3 measured
FrontierCodeNot measured14.7%Only MiniMax M3 measured
ALE-Bench2608.8640.0GPT-6.1 Terra
LMArena Text: codingNot measured1470Only MiniMax M3 measured
LMArena Text: software and ITNot measured1466Only MiniMax M3 measured
LMArena WebDev: React16571479GPT-6.1 Terra
LMArena WebDev: HTML17191455GPT-6.1 Terra
LMArena WebDev: from an imageNot measured1470Only MiniMax M3 measured
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for GPT-6.1 Terra and MiniMax M3
BenchmarkGPT-6.1 TerraMiniMax M3Leader
AA Intelligence Index51.018.7GPT-6.1 Terra
Epoch Capabilities IndexNot measured146.9Only MiniMax M3 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index12
Agentic work benchmarks for GPT-6.1 Terra and MiniMax M3
BenchmarkGPT-6.1 TerraMiniMax M3Leader
AA Agentic IndexNot measured29.5Only MiniMax M3 measured
Design Arena: agents building web appsNot measured1203Only MiniMax M3 measured
Design Arena: agents building full-stack appsNot measured1197Only MiniMax M3 measured
Design Arena: agents building mobile appsNot measured1167Only MiniMax M3 measured
Design Arena: agents building Android appsNot measured1161Only MiniMax M3 measured
Design Arena: agents building gamesNot measured1125Only MiniMax M3 measured
Design Arena: HTML slidesNot measured1077Only MiniMax M3 measured
Design Arena: PowerPoint slidesNot measured1161Only MiniMax M3 measured
Design Arena: spreadsheetsNot measured1068Only MiniMax M3 measured
LiveBench research73.9%Not measuredOnly GPT-6.1 Terra measured
LiveBench browser93.1%Not measuredOnly GPT-6.1 Terra measured
LiveBench long agentic48.6%Not measuredOnly GPT-6.1 Terra measured
Finance Agent (Vals AI)Not measured48.3%Only MiniMax M3 measured
Tax Agent Bench (Vals AI)15.2%20.6%MiniMax M3
Legal Research Bench (Vals AI)26.0%29.8%MiniMax M3
Harvey's Legal Agent Benchmark (Vals AI)1.7%Not measuredOnly GPT-6.1 Terra measured
Excel Modeling Benchmark (Vals AI)Not measured47.8%Only MiniMax M3 measured
τ²-Bench TelecomNot measured88.9%Only MiniMax M3 measured
APEX-Agents68.3%37.7%GPT-6.1 Terra
OSWorld 2.0Not measured4.6%Only MiniMax M3 measured
Vending-Bench 2Not measured$2,158Only MiniMax M3 measured
Neither model has a result on the other 21 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
Reasoning benchmarks for GPT-6.1 Terra and MiniMax M3
BenchmarkGPT-6.1 TerraMiniMax M3Leader
GPQA DiamondNot measured92.7%Only MiniMax M3 measured
LiveBench reasoning88.7%Not measuredOnly GPT-6.1 Terra measured
MMMU Pro (Vals AI)Not measured81.2%Only MiniMax M3 measured
GPQA Diamond (Artificial Analysis run)Not measured92.9%Only MiniMax M3 measured
Humanity's Last Exam (Artificial Analysis run)46.2%39.0%GPT-6.1 Terra
GPQA Diamond (Epoch AI run)94.3%90.9%GPT-6.1 Terra
SimpleBenchNot measured45.8%Only MiniMax M3 measured
Chess puzzlesNot measured13.0%Only MiniMax M3 measured
Mystery game puzzles74.0%8.0%GPT-6.1 Terra
EBR-bench78.1%Not measuredOnly GPT-6.1 Terra measured
LMArena Text: hard promptsNot measured1446Only MiniMax M3 measured
LMArena Text: expertNot measured1461Only MiniMax M3 measured
LMArena Text: hard prompts in EnglishNot measured1454Only MiniMax M3 measured
LMArena Vision: diagramsNot measured1266Only MiniMax M3 measured
LMArena Vision: homeworkNot measured1268Only MiniMax M3 measured
Humanity's Last Exam (Scale run)35.7%Not measuredOnly GPT-6.1 Terra measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index10
Math benchmarks for GPT-6.1 Terra and MiniMax M3
BenchmarkGPT-6.1 TerraMiniMax M3Leader
OTIS Mock AIME100.0%71.1%GPT-6.1 Terra
FrontierMath, tiers 1 to 390.9%Not measuredOnly GPT-6.1 Terra measured
FrontierMath, tier 492.7%Not measuredOnly GPT-6.1 Terra measured
ProofBenchNot measured18.0%Only MiniMax M3 measured
LMArena Text: mathNot measured1428Only MiniMax M3 measured
LMArena Text: mathematical workNot measured1447Only MiniMax M3 measured
Neither model has a result on the other 8 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
Knowledge benchmarks for GPT-6.1 Terra and MiniMax M3
BenchmarkGPT-6.1 TerraMiniMax M3Leader
MMLU ProNot measured84.2%Only MiniMax M3 measured
LegalBench (Vals AI)Not measured85.4%Only MiniMax M3 measured
CorpFin (Vals AI)Not measured68.1%Only MiniMax M3 measured
TaxEval (Vals AI)Not measured72.7%Only MiniMax M3 measured
MortgageTax (Vals AI)Not measured68.4%Only MiniMax M3 measured
MedCode (Vals AI)Not measured46.3%Only MiniMax M3 measured
SimpleQA Verified57.3%Not measuredOnly GPT-6.1 Terra measured
LMArena Text: scienceNot measured1450Only MiniMax M3 measured
LMArena Text: medicine and healthcareNot measured1438Only MiniMax M3 measured
LMArena Text: legal and governmentNot measured1434Only MiniMax M3 measured
LMArena Text: business and financeNot measured1433Only MiniMax M3 measured
Neither model has a result on the other 9 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index40
Web design benchmarks for GPT-6.1 Terra and MiniMax M3
BenchmarkGPT-6.1 TerraMiniMax M3Leader
Design Arena: websites12831256GPT-6.1 Terra
Design Arena: UI components12771240GPT-6.1 Terra
Design Arena: game dev13481210GPT-6.1 Terra
Design Arena: data vizNot measured1235Only MiniMax M3 measured
Design Arena: 3DNot measured1205Only MiniMax M3 measured
Design Arena: all code categories12951245GPT-6.1 Terra
Design Arena: SVGNot measured1158Only MiniMax M3 measured
Design Arena: ASCII artNot measured1157Only MiniMax M3 measured
LiveBench design82.3%Not measuredOnly GPT-6.1 Terra measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
General benchmarks for GPT-6.1 Terra and MiniMax M3
BenchmarkGPT-6.1 TerraMiniMax M3Leader
Vals Index60.5%Not measuredOnly GPT-6.1 Terra measured
LiveBench data analysis82.3%Not measuredOnly GPT-6.1 Terra measured
Public Benefits Bench (Vals AI)Not measured64.1%Only MiniMax M3 measured
SAGE (Vals AI)Not measured85.5%Only MiniMax M3 measured
MedScribe (Vals AI)Not measured87.3%Only MiniMax M3 measured
Vals Multimodal IndexNot measured60.0%Only MiniMax M3 measured
IFBenchNot measured82.9%Only MiniMax M3 measured
Long context reasoning (AA-LCR)82.7%83.0%MiniMax M3
DTBenchNot measured78.9%Only MiniMax M3 measured
LMCANot measured33.7%Only MiniMax M3 measured
Surface Evolver BenchNot measured55.0%Only MiniMax M3 measured
Furniture assembly79.2%Not measuredOnly GPT-6.1 Terra measured
LMArena TextNot measured1431Only MiniMax M3 measured
LMArena Text: instruction followingNot measured1431Only MiniMax M3 measured
LMArena Text: creative writingNot measured1400Only MiniMax M3 measured
LMArena VisionNot measured1251Only MiniMax M3 measured
LMArena Text: EnglishNot measured1442Only MiniMax M3 measured
LMArena Text: non-EnglishNot measured1418Only MiniMax M3 measured
LMArena Text: ChineseNot measured1465Only MiniMax M3 measured
LMArena Text: GermanNot measured1429Only MiniMax M3 measured
LMArena Text: JapaneseNot measured1376Only MiniMax M3 measured
LMArena Text: KoreanNot measured1371Only MiniMax M3 measured
LMArena Text: FrenchNot measured1441Only MiniMax M3 measured
LMArena Text: SpanishNot measured1430Only MiniMax M3 measured
LMArena Text: RussianNot measured1426Only MiniMax M3 measured
LMArena Text: PolishNot measured1424Only MiniMax M3 measured
LMArena Text: multi-turnNot measured1441Only MiniMax M3 measured
LMArena Text: longer queriesNot measured1444Only MiniMax M3 measured
LMArena Text: writing and languageNot measured1416Only MiniMax M3 measured
LMArena Text: entertainment and mediaNot measured1401Only MiniMax M3 measured
LMArena Vision: EnglishNot measured1263Only MiniMax M3 measured
LMArena Vision: ChineseNot measured1311Only MiniMax M3 measured
LMArena Vision: reading textNot measured1259Only MiniMax M3 measured
LMArena Vision: humorNot measured1235Only MiniMax M3 measured
LMArena Vision: recognizing thingsNot measured1197Only MiniMax M3 measured
LMArena Vision: creative writingNot measured1234Only MiniMax M3 measured
LMArena DocumentNot measured1435Only MiniMax M3 measured
MultiChallenge74.2%Not measuredOnly GPT-6.1 Terra measured
EQ-Bench 4Not measured1140Only MiniMax M3 measured
Neither model has a result on the other 9 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-6.1 Terra and MiniMax M3
BenchmarkGPT-6.1 TerraMiniMax M3Leader
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-6.1 Terra$0.0035Fits in one request
MiniMax M3$0.0009Fits in one request

MiniMax M3 costs less

Repository review

50K input + 3K output tokens

GPT-6.1 Terra$0.065Fits in one request
MiniMax M3$0.019Fits in one request

MiniMax M3 costs less

Agent loop

200K input + 10K output tokens

GPT-6.1 Terra$0.250Fits in one request
MiniMax M3$0.072Fits in one request

MiniMax M3 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-6.1 Terra and MiniMax M3
SpecificationOpenAI GPT-6.1 TerraMiniMax M3
MakerOpenAIMiniMax
WeightsNo public weights listedOpen weights
ReleasedOctober 26, 2026May 31, 2026
Context window1.05M1.05M
Input $/Mtok$1.00$0.30
Output $/Mtok$5.00$1.20
Coding index77.433.6
Independent measurements behind it45
Cost per solved taskNot computable$0.56
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-6.1 Terra better than MiniMax M3 for coding?

Pick GPT-6.1 Terra for coding: it scores 77.4 on the Vibe Coding Index against 33.6 for MiniMax M3, though on 4 benchmarks against 5. Pick MiniMax M3 for output tokens 4.2x cheaper ($1.20 vs $5.00 per million) and work measured by Tax Agent Bench (Vals AI) or Legal Research Bench (Vals AI), where it leads.

Which is cheaper, GPT-6.1 Terra or MiniMax M3?

GPT-6.1 Terra costs $1.00 per million input tokens and $5.00 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Cost per solved task is known for MiniMax M3 only.

Which has the bigger context window, GPT-6.1 Terra or MiniMax M3?

GPT-6.1 Terra, with 1.05M tokens against 1.05M.

How many benchmarks is the GPT-6.1 Terra vs MiniMax M3 comparison based on?

20 benchmarks have a result for both models as of October 29, 2026. GPT-6.1 Terra's coding index rests on 4 independent benchmarks and MiniMax M3's on 5. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/gpt-6-1-terra-vs-minimax-minimax-m3" title="GPT-6.1 Terra vs MiniMax M3, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/gpt-6-1-terra-vs-minimax-minimax-m3">LLMBenchmark.ai, GPT-6.1 Terra vs MiniMax M3</a></p>