Phi 4 vs Mistral Small 3.1 24B
Updated October 21, 2026. 27 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Neither model has a coding score yet, so the two cannot be ranked on coding.
Phi 4 has the edge where output tokens cost 4.0x less, and where what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.
- Shared results
- 27
- Phi 4 only
- 18
- Mistral Small 3.1 24B only
- 11
- Like-for-like categories
- 5 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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
No call
Only Phi 4 has a AA Intelligence Index result, 5.9.
Directional only
Long documents
Listed context window
Mistral Small 3.1 24B
Mistral Small 3.1 24B takes 128K tokens against 16K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Phi 4
Phi 4 $0.0001, Mistral Small 3.1 24B $0.0006 per turn.
List prices
At a glance
- Coding index
- Phi 4 not benchmarked, Mistral Small 3.1 24B not benchmarked.
- Widest category
- Coding, 12.6 points apart on average over 2 shared benchmarks.
- Widest single gap
- LMArena Text: entertainment and media: Phi 4 1162 against Mistral Small 3.1 24B 1250, 14.7 points apart on a 0 to 100 scale.
- Output price
- Phi 4 $0.14 against Mistral Small 3.1 24B $0.555 per million output tokens, 4.0x apart.
- Context window
- Phi 4 takes 16K tokens, Mistral Small 3.1 24B 128K.
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 | Mistral Small 3.1 24B | Ties |
|---|---|---|---|---|
| Coding | 0 | 2 | ||
| Reasoning | 0 | 3 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 4 | ||
| General | 0 | 16 | ||
| All shared boards | 0 | 27 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
| Benchmark | Phi 4 | Mistral Small 3.1 24B | 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 | 1309 | Mistral Small 3.1 24B |
| LMArena Text: software and IT | 1228 | 1301 | Mistral Small 3.1 24B |
| Neither model has a result on the other 34 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Phi 4 | Mistral Small 3.1 24B | Leader |
|---|---|---|---|
| AA Intelligence Index | 5.9 | Not measured | Only Phi 4 measured |
| 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 | Mistral Small 3.1 24B | 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 | Mistral Small 3.1 24B | 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 | 1278 | Mistral Small 3.1 24B |
| LMArena Text: expert | 1203 | 1257 | Mistral Small 3.1 24B |
| LMArena Text: hard prompts in English | 1230 | 1290 | Mistral Small 3.1 24B |
| LMArena Vision: diagrams | Not measured | 1119 | Only Mistral Small 3.1 24B measured |
| LMArena Vision: homework | Not measured | 1158 | Only Mistral Small 3.1 24B measured |
| Neither model has a result on the other 13 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Phi 4 | Mistral Small 3.1 24B | 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 | 1261 | Mistral Small 3.1 24B |
| LMArena Text: mathematical work | 1254 | 1271 | Mistral Small 3.1 24B |
| 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 | Mistral Small 3.1 24B | 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 | 1265 | Mistral Small 3.1 24B |
| LMArena Text: medicine and healthcare | 1202 | 1267 | Mistral Small 3.1 24B |
| LMArena Text: legal and government | 1241 | 1271 | Mistral Small 3.1 24B |
| LMArena Text: business and finance | 1199 | 1257 | Mistral Small 3.1 24B |
| 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 | Mistral Small 3.1 24B | 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 | Mistral Small 3.1 24B | 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 | 1277 | Mistral Small 3.1 24B |
| LMArena Text: instruction following | 1201 | 1263 | Mistral Small 3.1 24B |
| LMArena Text: creative writing | 1181 | 1252 | Mistral Small 3.1 24B |
| LMArena Vision | Not measured | 1136 | Only Mistral Small 3.1 24B measured |
| LMArena Text: English | 1231 | 1295 | Mistral Small 3.1 24B |
| LMArena Text: non-English | 1197 | 1255 | Mistral Small 3.1 24B |
| LMArena Text: Chinese | 1212 | 1253 | Mistral Small 3.1 24B |
| LMArena Text: German | 1222 | 1266 | Mistral Small 3.1 24B |
| LMArena Text: Japanese | 1158 | 1208 | Mistral Small 3.1 24B |
| LMArena Text: Korean | 1151 | 1207 | Mistral Small 3.1 24B |
| LMArena Text: French | 1224 | 1273 | Mistral Small 3.1 24B |
| LMArena Text: Spanish | 1234 | 1284 | Mistral Small 3.1 24B |
| LMArena Text: Russian | 1209 | 1263 | Mistral Small 3.1 24B |
| LMArena Text: Polish | Not measured | 1242 | Only Mistral Small 3.1 24B measured |
| LMArena Text: multi-turn | 1206 | 1270 | Mistral Small 3.1 24B |
| LMArena Text: longer queries | 1217 | 1299 | Mistral Small 3.1 24B |
| LMArena Text: writing and language | 1198 | 1268 | Mistral Small 3.1 24B |
| LMArena Text: entertainment and media | 1162 | 1250 | Mistral Small 3.1 24B |
| LMArena Vision: English | Not measured | 1157 | Only Mistral Small 3.1 24B measured |
| LMArena Vision: Chinese | Not measured | 1155 | Only Mistral Small 3.1 24B measured |
| LMArena Vision: reading text | Not measured | 1132 | Only Mistral Small 3.1 24B measured |
| LMArena Vision: humor | Not measured | 1142 | Only Mistral Small 3.1 24B measured |
| LMArena Vision: captioning | Not measured | 1153 | Only Mistral Small 3.1 24B measured |
| LMArena Vision: recognizing things | Not measured | 1155 | Only Mistral Small 3.1 24B measured |
| LMArena Vision: creative writing | Not measured | 1123 | Only Mistral Small 3.1 24B measured |
| Neither model has a result on the other 18 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Phi 4 | Mistral Small 3.1 24B | 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 | Mistral Small 3.1 24B |
|---|---|---|
| Maker | Microsoft | Mistral AI |
| Weights | Open weights | Open weights |
| Released | January 10, 2025 | March 17, 2025 |
| Context window | 16K | 128K |
| Input $/Mtok | $0.07 | $0.351 |
| Output $/Mtok | $0.14 | $0.555 |
| 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 Mistral Small 3.1 24B for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Phi 4 has the edge where output tokens cost 4.0x less, and where what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.
Which is cheaper, Phi 4 or Mistral Small 3.1 24B?
Phi 4 costs $0.07 per million input tokens and $0.14 per million output tokens; Mistral Small 3.1 24B costs $0.351 and $0.555. Cost per solved task is known for neither of them.
Which has the bigger context window, Phi 4 or Mistral Small 3.1 24B?
Mistral Small 3.1 24B, with 128K tokens against 16K.
How many benchmarks is the Phi 4 vs Mistral Small 3.1 24B comparison based on?
27 benchmarks have a result for both models as of October 21, 2026. Phi 4's coding index rests on 0 independent benchmarks and Mistral Small 3.1 24B's on 0. Where only one model has a result, the page says so instead of naming a winner.