GPT-4.1 vs MiniMax M3
MiniMax M3 leads GPT-4.1 on the Artificial Analysis Intelligence Index, 29.2 to 12.7, and MiniMax M3 costs 6.7x less per output token ($1.20 vs $8.00 per million). Updated October 22, 2026; 66 benchmarks have a result for both.
GPT-4.1 or MiniMax M3: which to pick
Only MiniMax M3 has a coding score, 39.2 on the Vibe Coding Index; GPT-4.1 has none, so the two cannot be ranked on coding.
Pick GPT-4.1 for a lower cost per solved task ($0.37 against $0.56) and work measured by TaxEval (Vals AI) or LMArena Vision: recognizing things, where it leads.
- Shared results
- 66
- GPT-4.1 only
- 26
- MiniMax M3 only
- 50
- Like-for-like categories
- 8 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.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only MiniMax M3 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
MiniMax M3
MiniMax M3 leads, 29.2 against 12.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only MiniMax M3 has a AA Agentic Index result, 29.5.
Directional only
Reasoning
GPQA Diamond
MiniMax M3
MiniMax M3 leads, 92.7% against 65.4%.
Same board, both measured
Math
AIME
No call
Only GPT-4.1 has a AIME result, 39.6%.
Directional only
Knowledge
MMLU Pro
MiniMax M3
MiniMax M3 leads, 84.2% against 80.5%.
Same board, both measured
Web design
Design Arena: websites
MiniMax M3
MiniMax M3 leads, 1257 against 1038.
Same board, both measured
Long documents
Listed context window
MiniMax M3
MiniMax M3 takes 1.05M tokens against 1.05M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M3
GPT-4.1 $0.0060, MiniMax M3 $0.0009 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GPT-4.1
GPT-4.1 $0.37, MiniMax M3 $0.56.
Published attempt cost and pass rate
At a glance
- Coding index
- GPT-4.1 not benchmarked, MiniMax M3 39.2 from 6 benchmarks.
- Widest category
- Agentic work, 41.8 points apart on average over 1 shared benchmark.
- Widest single gap
- Design Arena: 3D: GPT-4.1 849 against MiniMax M3 1208, 44.9 points apart on a 0 to 100 scale.
- Output price
- GPT-4.1 $8.00 against MiniMax M3 $1.20 per million output tokens, 6.7x apart.
- Context window
- GPT-4.1 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.
| Category | GPT-4.1 | Bars | MiniMax M3 | Ties |
|---|---|---|---|---|
| Coding | 0 | 5 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 12 | ||
| Math | 0 | 3 | ||
| Knowledge | 1 | 8 | ||
| Web design | 0 | 6 | ||
| General | 1 | 27 | ||
| All shared boards | 2 | 64 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index05
| Benchmark | GPT-4.1 | MiniMax M3 | Leader |
|---|---|---|---|
| Aider polyglot | 52.4% | Not measured | Only GPT-4.1 measured |
| SWE-bench Verified | 39.6% | Not measured | Only GPT-4.1 measured |
| SWE-bench Multimodal | 31.1% | Not measured | Only GPT-4.1 measured |
| LiveBench coding | Not measured | 70.9% | Only MiniMax M3 measured |
| LMArena WebDev | Not measured | 1482 | Only MiniMax M3 measured |
| AA Coding Index | Not measured | 58.6 | Only MiniMax M3 measured |
| LiveCodeBench (Vals AI) | 54.7% | 82.2% | MiniMax M3 |
| SWE-bench Verified (Vals AI) | Not measured | 75.0% | Only MiniMax M3 measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 1.0% | Only MiniMax M3 measured |
| Vibe Code Bench (Vals AI) | Not measured | 47.6% | Only MiniMax M3 measured |
| Code migration (Vals AI) | Not measured | 19.9% | Only MiniMax M3 measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 53.6% | Only MiniMax M3 measured |
| SWE-bench Multimodal (Vals AI) | Not measured | 33.3% | Only MiniMax M3 measured |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 9.2% | Only MiniMax M3 measured |
| SkillsBench (Vals AI) | Not measured | 51.5% | Only MiniMax M3 measured |
| CyberBench (Vals AI) | Not measured | 65.0% | Only MiniMax M3 measured |
| LiveCodeBench (Artificial Analysis run) | 45.7% | Not measured | Only GPT-4.1 measured |
| SciCode | Not measured | 47.1% | Only MiniMax M3 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 13.6% | 42.4% | MiniMax M3 |
| FrontierCode | Not measured | 14.7% | Only MiniMax M3 measured |
| WeirdML | 39.0% | Not measured | Only GPT-4.1 measured |
| ALE-Bench | 558.1 | 640.0 | MiniMax M3 |
| LMArena Text: coding | 1390 | 1470 | MiniMax M3 |
| LMArena Text: software and IT | 1391 | 1466 | MiniMax M3 |
| LMArena WebDev: React | Not measured | 1478 | Only MiniMax M3 measured |
| LMArena WebDev: HTML | Not measured | 1455 | Only MiniMax M3 measured |
| LMArena WebDev: from an image | Not measured | 1470 | Only MiniMax M3 measured |
| SciCode | 4.6% | Not measured | Only GPT-4.1 measured |
| Neither model has a result on the other 11 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-4.1 | MiniMax M3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 12.7 | 29.2 | MiniMax M3 |
| Epoch Capabilities Index | 136.7 | 146.9 | MiniMax M3 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-4.1 | MiniMax M3 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 29.5 | Only MiniMax M3 measured |
| Design Arena: agents building web apps | Not measured | 1200 | Only MiniMax M3 measured |
| Design Arena: agents building full-stack apps | Not measured | 1197 | Only MiniMax M3 measured |
| Design Arena: agents building mobile apps | Not measured | 1169 | Only MiniMax M3 measured |
| Design Arena: agents building Android apps | Not measured | 1159 | Only MiniMax M3 measured |
| Design Arena: agents building games | Not measured | 1159 | Only MiniMax M3 measured |
| Design Arena: HTML slides | Not measured | 1130 | Only MiniMax M3 measured |
| Design Arena: PowerPoint slides | Not measured | 1181 | Only MiniMax M3 measured |
| Design Arena: spreadsheets | Not measured | 1039 | Only MiniMax M3 measured |
| LiveBench research | Not measured | 68.0% | Only MiniMax M3 measured |
| LiveBench browser | Not measured | 8.0% | Only MiniMax M3 measured |
| LiveBench long agentic | Not measured | 12.4% | Only MiniMax M3 measured |
| Finance Agent (Vals AI) | Not measured | 48.3% | Only MiniMax M3 measured |
| Tax Agent Bench (Vals AI) | Not measured | 20.6% | Only MiniMax M3 measured |
| Legal Research Bench (Vals AI) | Not measured | 29.8% | Only MiniMax M3 measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 47.8% | Only MiniMax M3 measured |
| τ²-Bench Telecom | 47.1% | 88.9% | MiniMax M3 |
| APEX-Agents | Not measured | 37.7% | Only MiniMax M3 measured |
| OSWorld 2.0 | Not measured | 4.6% | Only MiniMax M3 measured |
| Vending-Bench 2 | Not measured | $2,158 | Only MiniMax M3 measured |
| Berkeley Function Calling Leaderboard (BFCL) | 54.0% | Not measured | Only GPT-4.1 measured |
| BrowseComp-Plus | 36.4% | Not measured | Only GPT-4.1 measured |
| Neither model has a result on the other 19 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index012
| Benchmark | GPT-4.1 | MiniMax M3 | Leader |
|---|---|---|---|
| GPQA Diamond | 65.4% | 92.7% | MiniMax M3 |
| LiveBench reasoning | Not measured | 74.5% | Only MiniMax M3 measured |
| MMMU Pro (Vals AI) | 72.4% | 81.2% | MiniMax M3 |
| GPQA Diamond (Artificial Analysis run) | 66.6% | 92.9% | MiniMax M3 |
| Humanity's Last Exam (Artificial Analysis run) | 4.2% | 39.0% | MiniMax M3 |
| GPQA Diamond (Epoch AI run) | 66.9% | 90.9% | MiniMax M3 |
| ARC-AGI | 5.5% | Not measured | Only GPT-4.1 measured |
| ARC-AGI-2 | 0.4% | Not measured | Only GPT-4.1 measured |
| SimpleBench | 27.0% | 45.8% | MiniMax M3 |
| Chess puzzles | 3.0% | 13.0% | MiniMax M3 |
| Mystery game puzzles | Not measured | 8.0% | Only MiniMax M3 measured |
| LMArena Text: hard prompts | 1384 | 1447 | MiniMax M3 |
| LMArena Text: expert | 1364 | 1461 | MiniMax M3 |
| LMArena Text: hard prompts in English | 1393 | 1455 | MiniMax M3 |
| LMArena Vision: diagrams | 1215 | 1266 | MiniMax M3 |
| LMArena Vision: homework | 1248 | 1268 | MiniMax M3 |
| Kagi LLM Benchmark | 52.3% | Not measured | Only GPT-4.1 measured |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | GPT-4.1 | MiniMax M3 | Leader |
|---|---|---|---|
| AIME | 39.6% | Not measured | Only GPT-4.1 measured |
| MATH 500 (Vals AI) | 87.2% | Not measured | Only GPT-4.1 measured |
| MGSM (Vals AI) | 87.7% | Not measured | Only GPT-4.1 measured |
| AA Math Index | 34.7 | Not measured | Only GPT-4.1 measured |
| AIME 2025 (Artificial Analysis run) | 34.7% | Not measured | Only GPT-4.1 measured |
| OTIS Mock AIME | 38.3% | 71.1% | MiniMax M3 |
| FrontierMath, tiers 1 to 3 | 6.0% | Not measured | Only GPT-4.1 measured |
| ProofBench | Not measured | 18.0% | Only MiniMax M3 measured |
| MATH level 5 | 83.0% | Not measured | Only GPT-4.1 measured |
| LMArena Text: math | 1369 | 1429 | MiniMax M3 |
| LMArena Text: mathematical work | 1360 | 1448 | MiniMax M3 |
| Neither model has a result on the other 2 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index18
| Benchmark | GPT-4.1 | MiniMax M3 | Leader |
|---|---|---|---|
| MMLU Pro | 80.5% | 84.2% | MiniMax M3 |
| LegalBench (Vals AI) | 83.1% | 85.4% | MiniMax M3 |
| CaseLaw (Vals AI) | 69.9% | Not measured | Only GPT-4.1 measured |
| CorpFin (Vals AI) | 63.0% | 68.1% | MiniMax M3 |
| TaxEval (Vals AI) | 75.1% | 72.7% | GPT-4.1 |
| MortgageTax (Vals AI) | 65.9% | 68.4% | MiniMax M3 |
| MedQA (Vals AI) | 91.2% | Not measured | Only GPT-4.1 measured |
| MedCode (Vals AI) | Not measured | 46.3% | Only MiniMax M3 measured |
| MMLU Pro (Artificial Analysis run) | 80.6% | Not measured | Only GPT-4.1 measured |
| SimpleQA Verified | 31.1% | Not measured | Only GPT-4.1 measured |
| GeoBench | 72.0% | Not measured | Only GPT-4.1 measured |
| LMArena Text: science | 1382 | 1452 | MiniMax M3 |
| LMArena Text: medicine and healthcare | 1379 | 1441 | MiniMax M3 |
| LMArena Text: legal and government | 1399 | 1437 | MiniMax M3 |
| LMArena Text: business and finance | 1369 | 1434 | MiniMax M3 |
| FACTS Benchmark Suite | 45.8% | Not measured | Only GPT-4.1 measured |
| Neither model has a result on the other 2 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | GPT-4.1 | MiniMax M3 | Leader |
|---|---|---|---|
| Design Arena: websites | 1038 | 1257 | MiniMax M3 |
| Design Arena: UI components | 997 | 1243 | MiniMax M3 |
| Design Arena: game dev | 1079 | 1211 | MiniMax M3 |
| Design Arena: data viz | 1104 | 1236 | MiniMax M3 |
| Design Arena: 3D | 849 | 1208 | MiniMax M3 |
| Design Arena: all code categories | 1025 | 1246 | MiniMax M3 |
| Design Arena: SVG | Not measured | 1160 | Only MiniMax M3 measured |
| Design Arena: ASCII art | Not measured | 1161 | Only MiniMax M3 measured |
| LiveBench design | Not measured | 66.2% | Only MiniMax M3 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index127
| Benchmark | GPT-4.1 | MiniMax M3 | Leader |
|---|---|---|---|
| LiveBench data analysis | Not measured | 76.2% | Only MiniMax M3 measured |
| Public Benefits Bench (Vals AI) | Not measured | 64.1% | Only MiniMax M3 measured |
| SAGE (Vals AI) | Not measured | 50.6% | Only MiniMax M3 measured |
| MedScribe (Vals AI) | Not measured | 87.3% | Only MiniMax M3 measured |
| Vals Multimodal Index | Not measured | 60.0% | Only MiniMax M3 measured |
| IFBench | 43.0% | 82.9% | MiniMax M3 |
| Long context reasoning (AA-LCR) | 68.3% | 83.0% | MiniMax M3 |
| DTBench | 68.3% | 78.9% | MiniMax M3 |
| LMCA | 25.6% | 33.7% | MiniMax M3 |
| Fiction.LiveBench | 63.9% | Not measured | Only GPT-4.1 measured |
| Surface Evolver Bench | Not measured | 55.0% | Only MiniMax M3 measured |
| LMArena Text | 1383 | 1433 | MiniMax M3 |
| LMArena Text: instruction following | 1367 | 1433 | MiniMax M3 |
| LMArena Text: creative writing | 1363 | 1404 | MiniMax M3 |
| LMArena Vision | 1210 | 1251 | MiniMax M3 |
| LMArena Text: English | 1392 | 1443 | MiniMax M3 |
| LMArena Text: non-English | 1370 | 1420 | MiniMax M3 |
| LMArena Text: Chinese | 1382 | 1466 | MiniMax M3 |
| LMArena Text: German | 1381 | 1428 | MiniMax M3 |
| LMArena Text: Japanese | 1319 | 1380 | MiniMax M3 |
| LMArena Text: Korean | 1338 | 1373 | MiniMax M3 |
| LMArena Text: French | 1382 | 1444 | MiniMax M3 |
| LMArena Text: Spanish | 1376 | 1433 | MiniMax M3 |
| LMArena Text: Russian | 1377 | 1426 | MiniMax M3 |
| LMArena Text: Polish | 1389 | 1423 | MiniMax M3 |
| LMArena Text: multi-turn | 1397 | 1443 | MiniMax M3 |
| LMArena Text: longer queries | 1385 | 1446 | MiniMax M3 |
| LMArena Text: writing and language | 1371 | 1419 | MiniMax M3 |
| LMArena Text: entertainment and media | 1365 | 1403 | MiniMax M3 |
| LMArena Vision: English | 1209 | 1263 | MiniMax M3 |
| LMArena Vision: Chinese | 1226 | 1311 | MiniMax M3 |
| LMArena Vision: reading text | 1218 | 1259 | MiniMax M3 |
| LMArena Vision: humor | 1196 | 1235 | MiniMax M3 |
| LMArena Vision: captioning | 1207 | Not measured | Only GPT-4.1 measured |
| LMArena Vision: recognizing things | 1208 | 1197 | GPT-4.1 |
| LMArena Vision: creative writing | 1210 | 1234 | MiniMax M3 |
| LMArena Document | Not measured | 1435 | Only 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
| Benchmark | GPT-4.1 | MiniMax M3 | Leader |
|---|---|---|---|
| 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
MiniMax M3 costs less
Repository review
50K input + 3K output tokens
MiniMax M3 costs less
Agent loop
200K input + 10K output tokens
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.
| Specification | OpenAI GPT-4.1 | MiniMax M3 |
|---|---|---|
| Maker | OpenAI | MiniMax |
| Weights | No public weights listed | Open weights |
| Released | April 14, 2025 | May 31, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $2.00 | $0.30 |
| Output $/Mtok | $8.00 | $1.20 |
| Coding index | Not benchmarked | 39.2 |
| Independent measurements behind it | 0 | 6 |
| Cost per solved task | $0.37 | $0.56 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-4.1 better than MiniMax M3 for coding?
Only MiniMax M3 has a coding score, 39.2 on the Vibe Coding Index; GPT-4.1 has none, so the two cannot be ranked on coding. Pick GPT-4.1 for a lower cost per solved task ($0.37 against $0.56) and work measured by TaxEval (Vals AI) or LMArena Vision: recognizing things, where it leads.
Which is cheaper, GPT-4.1 or MiniMax M3?
GPT-4.1 costs $2.00 per million input tokens and $8.00 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Per solved SWE-bench Verified task, GPT-4.1 costs $0.37 and MiniMax M3 $0.56.
Which has the bigger context window, GPT-4.1 or MiniMax M3?
MiniMax M3, with 1.05M tokens against 1.05M.
How many benchmarks is the GPT-4.1 vs MiniMax M3 comparison based on?
66 benchmarks have a result for both models as of October 22, 2026. GPT-4.1's coding index rests on 0 independent benchmarks and MiniMax M3's on 6. Where only one model has a result, the page says so instead of naming a winner.