Phi 4 vs MiniMax M1
MiniMax M1 leads Phi 4 on the Artificial Analysis Intelligence Index, 11.7 to 5.9, and Phi 4 costs 15.7x less per output token ($0.14 vs $2.20 per million). Updated October 21, 2026; 28 benchmarks have a result for both.
Phi 4 or MiniMax M1: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Phi 4 for output tokens 15.7x cheaper ($0.14 vs $2.20 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
- Shared results
- 28
- Phi 4 only
- 17
- MiniMax M1 only
- 1
- 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.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
MiniMax M1
MiniMax M1 leads, 11.7 against 5.9.
Same board, both measured
Long documents
Listed context window
MiniMax M1
MiniMax M1 takes 1M tokens against 16K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Phi 4
Phi 4 $0.0001, MiniMax M1 $0.0015 per turn.
List prices
At a glance
- Coding index
- Phi 4 not benchmarked, MiniMax M1 not benchmarked.
- Widest category
- Coding, 21.6 points apart on average over 2 shared benchmarks.
- Widest single gap
- LMArena Text: medicine and healthcare: Phi 4 1202 against MiniMax M1 1355, 25.6 points apart on a 0 to 100 scale.
- Output price
- Phi 4 $0.14 against MiniMax M1 $2.20 per million output tokens, 15.7x apart.
- Context window
- Phi 4 takes 16K tokens, MiniMax M1 1M.
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 | Phi 4 | Bars | MiniMax M1 | Ties |
|---|---|---|---|---|
| Coding | 0 | 2 | ||
| Intelligence | 0 | 1 | ||
| Reasoning | 0 | 3 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 4 | ||
| General | 0 | 16 | ||
| All shared boards | 0 | 28 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
| Benchmark | Phi 4 | MiniMax M1 | Leader |
|---|---|---|---|
| LiveCodeBench (Artificial Analysis run) | 23.1% | Not measured | Only Phi 4 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 3.8% | Not measured | Only Phi 4 measured |
| LMArena Text: coding | 1231 | 1359 | MiniMax M1 |
| LMArena Text: software and IT | 1228 | 1359 | MiniMax M1 |
| Neither model has a result on the other 34 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Phi 4 | MiniMax M1 | Leader |
|---|---|---|---|
| AA Intelligence Index | 5.9 | 11.7 | MiniMax M1 |
| Epoch Capabilities Index | 130.5 | Not measured | Only Phi 4 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Phi 4 | MiniMax M1 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 0.0% | Not measured | Only Phi 4 measured |
| BALROG | 11.6% | Not measured | Only Phi 4 measured |
| Neither model has a result on the other 37 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | Phi 4 | MiniMax M1 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 57.5% | Not measured | Only Phi 4 measured |
| Humanity's Last Exam (Artificial Analysis run) | 3.8% | Not measured | Only Phi 4 measured |
| GPQA Diamond (Epoch AI run) | 56.1% | Not measured | Only Phi 4 measured |
| LMArena Text: hard prompts | 1220 | 1339 | MiniMax M1 |
| LMArena Text: expert | 1203 | 1317 | MiniMax M1 |
| LMArena Text: hard prompts in English | 1230 | 1353 | MiniMax M1 |
| Neither model has a result on the other 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Phi 4 | MiniMax M1 | Leader |
|---|---|---|---|
| AA Math Index | 18.0 | Not measured | Only Phi 4 measured |
| AIME 2025 (Artificial Analysis run) | 18.0% | Not measured | Only Phi 4 measured |
| OTIS Mock AIME | 13.8% | Not measured | Only Phi 4 measured |
| MATH level 5 | 64.9% | Not measured | Only Phi 4 measured |
| LMArena Text: math | 1246 | 1361 | MiniMax M1 |
| LMArena Text: mathematical work | 1254 | 1363 | MiniMax M1 |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Phi 4 | MiniMax M1 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 71.4% | Not measured | Only Phi 4 measured |
| MMLU | 84.8% | Not measured | Only Phi 4 measured |
| LMArena Text: science | 1206 | 1354 | MiniMax M1 |
| LMArena Text: medicine and healthcare | 1202 | 1355 | MiniMax M1 |
| LMArena Text: legal and government | 1241 | 1337 | MiniMax M1 |
| LMArena Text: business and finance | 1199 | 1319 | MiniMax M1 |
| Neither model has a result on the other 11 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Phi 4 | MiniMax M1 | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index016
| Benchmark | Phi 4 | MiniMax M1 | Leader |
|---|---|---|---|
| IFBench | 23.5% | Not measured | Only Phi 4 measured |
| Long context reasoning (AA-LCR) | 0.0% | Not measured | Only Phi 4 measured |
| Creative writing (Lech Mazur) | 62.6% | Not measured | Only Phi 4 measured |
| LMArena Text | 1217 | 1343 | MiniMax M1 |
| LMArena Text: instruction following | 1201 | 1312 | MiniMax M1 |
| LMArena Text: creative writing | 1181 | 1297 | MiniMax M1 |
| LMArena Text: English | 1231 | 1363 | MiniMax M1 |
| LMArena Text: non-English | 1197 | 1319 | MiniMax M1 |
| LMArena Text: Chinese | 1212 | 1360 | MiniMax M1 |
| LMArena Text: German | 1222 | 1350 | MiniMax M1 |
| LMArena Text: Japanese | 1158 | 1217 | MiniMax M1 |
| LMArena Text: Korean | 1151 | 1266 | MiniMax M1 |
| LMArena Text: French | 1224 | 1370 | MiniMax M1 |
| LMArena Text: Spanish | 1234 | 1353 | MiniMax M1 |
| LMArena Text: Russian | 1209 | 1329 | MiniMax M1 |
| LMArena Text: Polish | Not measured | 1329 | Only MiniMax M1 measured |
| LMArena Text: multi-turn | 1206 | 1335 | MiniMax M1 |
| LMArena Text: longer queries | 1217 | 1326 | MiniMax M1 |
| LMArena Text: writing and language | 1198 | 1311 | MiniMax M1 |
| LMArena Text: entertainment and media | 1162 | 1303 | MiniMax M1 |
| Neither model has a result on the other 26 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Phi 4 | MiniMax M1 | 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
Phi 4 costs less
Repository review
50K input + 3K output tokens
Phi 4 costs less
Agent loop
200K input + 10K output tokens
Phi 4 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 | Microsoft Phi 4 | MiniMax M1 |
|---|---|---|
| Maker | Microsoft | MiniMax |
| Weights | Open weights | No public weights listed |
| Released | January 10, 2025 | June 17, 2025 |
| Context window | 16K | 1M |
| Input $/Mtok | $0.07 | $0.40 |
| Output $/Mtok | $0.14 | $2.20 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Phi 4 better than MiniMax M1 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Phi 4 for output tokens 15.7x cheaper ($0.14 vs $2.20 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
Which is cheaper, Phi 4 or MiniMax M1?
Phi 4 costs $0.07 per million input tokens and $0.14 per million output tokens; MiniMax M1 costs $0.40 and $2.20. Cost per solved task is known for neither of them.
Which has the bigger context window, Phi 4 or MiniMax M1?
MiniMax M1, with 1M tokens against 16K.
How many benchmarks is the Phi 4 vs MiniMax M1 comparison based on?
28 benchmarks have a result for both models as of October 21, 2026. Phi 4's coding index rests on 0 independent benchmarks and MiniMax M1's on 0. Where only one model has a result, the page says so instead of naming a winner.