MiniMax M3 vs o4 Mini
MiniMax M3 leads o4 Mini on the Artificial Analysis Intelligence Index, 29.2 to 16.7, and MiniMax M3 costs 3.7x less per output token ($1.20 vs $4.40 per million). Updated October 22, 2026; 69 benchmarks have a result for both.
MiniMax M3 or o4 Mini: which to pick
Only MiniMax M3 has a coding score, 39.2 on the Vibe Coding Index; o4 Mini has none, so the two cannot be ranked on coding.
Pick o4 Mini for work measured by LiveCodeBench (Vals AI) or Chess puzzles, where it leads.
- Shared results
- 69
- MiniMax M3 only
- 47
- o4 Mini only
- 29
- 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 16.7.
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 74.5%.
Same board, both measured
Math
AIME
No call
Only o4 Mini has a AIME result, 83.7%.
Directional only
Knowledge
MMLU Pro
MiniMax M3
MiniMax M3 leads, 84.2% against 80.6%.
Same board, both measured
Web design
Design Arena: websites
MiniMax M3
MiniMax M3 leads, 1257 against 985.
Same board, both measured
Long documents
Listed context window
MiniMax M3
MiniMax M3 takes 1.05M tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M3
MiniMax M3 $0.0009, o4 Mini $0.0033 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only MiniMax M3 has the number, $0.56.
Directional only
At a glance
- Coding index
- MiniMax M3 39.2 from 6 benchmarks, o4 Mini not benchmarked.
- Widest category
- Web design, 33.5 points apart on average over 6 shared benchmarks.
- Widest single gap
- Design Arena: 3D: MiniMax M3 1208 against o4 Mini 854, 44.3 points apart on a 0 to 100 scale.
- Output price
- MiniMax M3 $1.20 against o4 Mini $4.40 per million output tokens, 3.7x apart.
- Context window
- MiniMax M3 takes 1.05M tokens, o4 Mini 200K.
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 | MiniMax M3 | Bars | o4 Mini | Ties |
|---|---|---|---|---|
| Coding | 3 | 1 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 12 | 1 | ||
| Math | 2 | 1 | ||
| Knowledge | 9 | 1 | ||
| Web design | 6 | 0 | ||
| General | 29 | 1 | ||
| All shared boards | 64 | 5 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index31
| Benchmark | MiniMax M3 | o4 Mini | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 72.0% | Only o4 Mini measured |
| SWE-bench Verified | Not measured | 64.6% | Only o4 Mini measured |
| SWE-bench Multimodal | Not measured | 33.9% | Only o4 Mini measured |
| LiveBench coding | 70.9% | Not measured | Only MiniMax M3 measured |
| LMArena WebDev | 1482 | Not measured | Only MiniMax M3 measured |
| AA Coding Index | 58.6 | Not measured | Only MiniMax M3 measured |
| LiveCodeBench (Vals AI) | 82.2% | 82.2% | o4 Mini |
| SWE-bench Verified (Vals AI) | 75.0% | Not measured | Only MiniMax M3 measured |
| Terminal-Bench 4 (Vals AI) | 1.0% | Not measured | Only MiniMax M3 measured |
| Vibe Code Bench (Vals AI) | 47.6% | Not measured | Only MiniMax M3 measured |
| Code migration (Vals AI) | 19.9% | Not measured | Only MiniMax M3 measured |
| Terminal-Bench 2.1 (Vals AI) | 53.6% | Not measured | Only MiniMax M3 measured |
| SWE-bench Multimodal (Vals AI) | 33.3% | Not measured | Only MiniMax M3 measured |
| Vibe Code Bench 1-100 (Vals AI) | 9.2% | Not measured | Only MiniMax M3 measured |
| SkillsBench (Vals AI) | 51.5% | Not measured | Only MiniMax M3 measured |
| CyberBench (Vals AI) | 65.0% | Not measured | Only MiniMax M3 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 85.9% | Only o4 Mini measured |
| SciCode | 47.1% | Not measured | Only MiniMax M3 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 42.4% | 15.2% | MiniMax M3 |
| FrontierCode | 14.7% | Not measured | Only MiniMax M3 measured |
| GSO-Bench | Not measured | 3.6% | Only o4 Mini measured |
| WeirdML | Not measured | 52.6% | Only o4 Mini measured |
| ALE-Bench | 640.0 | Not measured | Only MiniMax M3 measured |
| LMArena Text: coding | 1470 | 1368 | MiniMax M3 |
| LMArena Text: software and IT | 1466 | 1367 | MiniMax M3 |
| LMArena WebDev: React | 1478 | Not measured | Only MiniMax M3 measured |
| LMArena WebDev: HTML | 1455 | Not measured | Only MiniMax M3 measured |
| LMArena WebDev: from an image | 1470 | Not measured | Only MiniMax M3 measured |
| SciCode | Not measured | 10.8% | Only o4 Mini measured |
| Neither model has a result on the other 10 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | MiniMax M3 | o4 Mini | Leader |
|---|---|---|---|
| AA Intelligence Index | 29.2 | 16.7 | MiniMax M3 |
| Epoch Capabilities Index | 146.9 | 145.5 | MiniMax M3 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | MiniMax M3 | o4 Mini | Leader |
|---|---|---|---|
| AA Agentic Index | 29.5 | Not measured | Only MiniMax M3 measured |
| Design Arena: agents building web apps | 1200 | Not measured | Only MiniMax M3 measured |
| Design Arena: agents building full-stack apps | 1197 | Not measured | Only MiniMax M3 measured |
| Design Arena: agents building mobile apps | 1169 | Not measured | Only MiniMax M3 measured |
| Design Arena: agents building Android apps | 1159 | Not measured | Only MiniMax M3 measured |
| Design Arena: agents building games | 1158 | Not measured | Only MiniMax M3 measured |
| Design Arena: HTML slides | 1130 | Not measured | Only MiniMax M3 measured |
| Design Arena: PowerPoint slides | 1181 | Not measured | Only MiniMax M3 measured |
| Design Arena: spreadsheets | 1028 | Not measured | Only MiniMax M3 measured |
| LiveBench research | 68.0% | Not measured | Only MiniMax M3 measured |
| LiveBench browser | 8.0% | Not measured | Only MiniMax M3 measured |
| LiveBench long agentic | 12.4% | Not measured | Only MiniMax M3 measured |
| Finance Agent (Vals AI) | 48.3% | Not measured | Only MiniMax M3 measured |
| Tax Agent Bench (Vals AI) | 20.6% | Not measured | Only MiniMax M3 measured |
| Legal Research Bench (Vals AI) | 29.8% | Not measured | Only MiniMax M3 measured |
| Excel Modeling Benchmark (Vals AI) | 47.8% | Not measured | Only MiniMax M3 measured |
| τ²-Bench Telecom | 88.9% | 55.6% | MiniMax M3 |
| APEX-Agents | 37.7% | Not measured | Only MiniMax M3 measured |
| METR time horizons | Not measured | 63.9% | Only o4 Mini measured |
| OSWorld 2.0 | 4.6% | Not measured | Only MiniMax M3 measured |
| Vending-Bench 2 | $2,158 | Not measured | Only MiniMax M3 measured |
| Berkeley Function Calling Leaderboard (BFCL) | Not measured | 53.2% | Only o4 Mini measured |
| Neither model has a result on the other 19 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index121
| Benchmark | MiniMax M3 | o4 Mini | Leader |
|---|---|---|---|
| GPQA Diamond | 92.7% | 74.5% | MiniMax M3 |
| LiveBench reasoning | 74.5% | Not measured | Only MiniMax M3 measured |
| MMMU Pro (Vals AI) | 81.2% | 79.7% | MiniMax M3 |
| GPQA Diamond (Artificial Analysis run) | 92.9% | 78.4% | MiniMax M3 |
| Humanity's Last Exam (Artificial Analysis run) | 39.0% | 16.5% | MiniMax M3 |
| GPQA Diamond (Epoch AI run) | 90.9% | 79.6% | MiniMax M3 |
| ARC-AGI | Not measured | 58.7% | Only o4 Mini measured |
| ARC-AGI-2 | Not measured | 6.1% | Only o4 Mini measured |
| SimpleBench | 45.8% | 38.7% | MiniMax M3 |
| Chess puzzles | 13.0% | 22.0% | o4 Mini |
| Mystery game puzzles | 8.0% | 5.0% | MiniMax M3 |
| VPCT | Not measured | 57.5% | Only o4 Mini measured |
| LMArena Text: hard prompts | 1447 | 1351 | MiniMax M3 |
| LMArena Text: expert | 1461 | 1343 | MiniMax M3 |
| LMArena Text: hard prompts in English | 1455 | 1366 | MiniMax M3 |
| LMArena Vision: diagrams | 1266 | 1197 | MiniMax M3 |
| LMArena Vision: homework | 1268 | 1234 | MiniMax M3 |
| Kagi LLM Benchmark | Not measured | 67.6% | Only o4 Mini measured |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | MiniMax M3 | o4 Mini | Leader |
|---|---|---|---|
| AIME | Not measured | 83.7% | Only o4 Mini measured |
| MATH 500 (Vals AI) | Not measured | 94.2% | Only o4 Mini measured |
| MGSM (Vals AI) | Not measured | 93.4% | Only o4 Mini measured |
| AA Math Index | Not measured | 90.7 | Only o4 Mini measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 90.7% | Only o4 Mini measured |
| OTIS Mock AIME | 71.1% | 81.7% | o4 Mini |
| FrontierMath, tiers 1 to 3 | Not measured | 36.1% | Only o4 Mini measured |
| FrontierMath, tier 4 | Not measured | 4.9% | Only o4 Mini measured |
| ProofBench | 18.0% | Not measured | Only MiniMax M3 measured |
| MATH level 5 | Not measured | 97.8% | Only o4 Mini measured |
| LMArena Text: math | 1429 | 1389 | MiniMax M3 |
| LMArena Text: mathematical work | 1448 | 1379 | MiniMax M3 |
| Neither model has a result on the other 1 board here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index91
| Benchmark | MiniMax M3 | o4 Mini | Leader |
|---|---|---|---|
| MMLU Pro | 84.2% | 80.6% | MiniMax M3 |
| LegalBench (Vals AI) | 85.4% | 79.2% | MiniMax M3 |
| CorpFin (Vals AI) | 68.1% | 59.0% | MiniMax M3 |
| TaxEval (Vals AI) | 72.7% | 74.8% | o4 Mini |
| MortgageTax (Vals AI) | 68.4% | 64.8% | MiniMax M3 |
| MedQA (Vals AI) | Not measured | 96.0% | Only o4 Mini measured |
| MedCode (Vals AI) | 46.3% | 33.8% | MiniMax M3 |
| MMLU Pro (Artificial Analysis run) | Not measured | 83.2% | Only o4 Mini measured |
| SimpleQA Verified | Not measured | 19.6% | Only o4 Mini measured |
| GeoBench | Not measured | 64.0% | Only o4 Mini measured |
| LMArena Text: science | 1452 | 1354 | MiniMax M3 |
| LMArena Text: medicine and healthcare | 1441 | 1361 | MiniMax M3 |
| LMArena Text: legal and government | 1437 | 1350 | MiniMax M3 |
| LMArena Text: business and finance | 1434 | 1325 | MiniMax M3 |
| FACTS Benchmark Suite | Not measured | 28.1% | Only o4 Mini measured |
| Neither model has a result on the other 3 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | MiniMax M3 | o4 Mini | Leader |
|---|---|---|---|
| Design Arena: websites | 1257 | 985 | MiniMax M3 |
| Design Arena: UI components | 1242 | 983 | MiniMax M3 |
| Design Arena: game dev | 1210 | 1003 | MiniMax M3 |
| Design Arena: data viz | 1236 | 991 | MiniMax M3 |
| Design Arena: 3D | 1208 | 854 | MiniMax M3 |
| Design Arena: all code categories | 1247 | 976 | MiniMax M3 |
| Design Arena: SVG | 1161 | Not measured | Only MiniMax M3 measured |
| Design Arena: ASCII art | 1161 | Not measured | Only MiniMax M3 measured |
| LiveBench design | 66.2% | Not measured | Only MiniMax M3 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index291
| Benchmark | MiniMax M3 | o4 Mini | Leader |
|---|---|---|---|
| LiveBench data analysis | 76.2% | Not measured | Only MiniMax M3 measured |
| Public Benefits Bench (Vals AI) | 64.1% | Not measured | Only MiniMax M3 measured |
| SAGE (Vals AI) | 50.6% | 41.1% | MiniMax M3 |
| MedScribe (Vals AI) | 87.3% | 69.1% | MiniMax M3 |
| Vals Multimodal Index | 60.0% | Not measured | Only MiniMax M3 measured |
| IFBench | 82.9% | 68.7% | MiniMax M3 |
| Long context reasoning (AA-LCR) | 83.0% | 61.0% | MiniMax M3 |
| DTBench | 78.9% | 77.6% | MiniMax M3 |
| LMCA | 33.7% | 26.5% | MiniMax M3 |
| Fiction.LiveBench | Not measured | 77.8% | Only o4 Mini measured |
| Creative writing (Lech Mazur) | Not measured | 75.0% | Only o4 Mini measured |
| Surface Evolver Bench | 55.0% | Not measured | Only MiniMax M3 measured |
| LMArena Text | 1433 | 1353 | MiniMax M3 |
| LMArena Text: instruction following | 1433 | 1320 | MiniMax M3 |
| LMArena Text: creative writing | 1404 | 1294 | MiniMax M3 |
| LMArena Vision | 1251 | 1194 | MiniMax M3 |
| LMArena Text: English | 1443 | 1367 | MiniMax M3 |
| LMArena Text: non-English | 1420 | 1337 | MiniMax M3 |
| LMArena Text: Chinese | 1466 | 1354 | MiniMax M3 |
| LMArena Text: German | 1428 | 1336 | MiniMax M3 |
| LMArena Text: Japanese | 1380 | 1308 | MiniMax M3 |
| LMArena Text: Korean | 1373 | 1312 | MiniMax M3 |
| LMArena Text: French | 1444 | 1364 | MiniMax M3 |
| LMArena Text: Spanish | 1433 | 1346 | MiniMax M3 |
| LMArena Text: Russian | 1426 | 1334 | MiniMax M3 |
| LMArena Text: Polish | 1423 | 1358 | MiniMax M3 |
| LMArena Text: multi-turn | 1443 | 1350 | MiniMax M3 |
| LMArena Text: longer queries | 1446 | 1315 | MiniMax M3 |
| LMArena Text: writing and language | 1419 | 1316 | MiniMax M3 |
| LMArena Text: entertainment and media | 1403 | 1308 | MiniMax M3 |
| LMArena Vision: English | 1263 | 1200 | MiniMax M3 |
| LMArena Vision: Chinese | 1311 | 1218 | MiniMax M3 |
| LMArena Vision: reading text | 1259 | 1197 | MiniMax M3 |
| LMArena Vision: humor | 1235 | 1199 | MiniMax M3 |
| LMArena Vision: captioning | Not measured | 1204 | Only o4 Mini measured |
| LMArena Vision: recognizing things | 1197 | 1218 | o4 Mini |
| LMArena Vision: creative writing | 1234 | 1166 | MiniMax M3 |
| LMArena Document | 1435 | Not measured | Only MiniMax M3 measured |
| Neither model has a result on the other 8 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | MiniMax M3 | o4 Mini | 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 | MiniMax M3 | OpenAI o4 Mini |
|---|---|---|
| Maker | MiniMax | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | May 31, 2026 | April 16, 2025 |
| Context window | 1.05M | 200K |
| Input $/Mtok | $0.30 | $1.10 |
| Output $/Mtok | $1.20 | $4.40 |
| Coding index | 39.2 | Not benchmarked |
| Independent measurements behind it | 6 | 0 |
| Cost per solved task | $0.56 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is MiniMax M3 better than o4 Mini for coding?
Only MiniMax M3 has a coding score, 39.2 on the Vibe Coding Index; o4 Mini has none, so the two cannot be ranked on coding. Pick o4 Mini for work measured by LiveCodeBench (Vals AI) or Chess puzzles, where it leads.
Which is cheaper, MiniMax M3 or o4 Mini?
MiniMax M3 costs $0.30 per million input tokens and $1.20 per million output tokens; o4 Mini costs $1.10 and $4.40. Cost per solved task is known for MiniMax M3 only.
Which has the bigger context window, MiniMax M3 or o4 Mini?
MiniMax M3, with 1.05M tokens against 200K.
How many benchmarks is the MiniMax M3 vs o4 Mini comparison based on?
69 benchmarks have a result for both models as of October 22, 2026. MiniMax M3's coding index rests on 6 independent benchmarks and o4 Mini's on 0. Where only one model has a result, the page says so instead of naming a winner.