Phi 4 vs Mistral Small 4
Mistral Small 4 leads Phi 4 on the Artificial Analysis Intelligence Index, 11.3 to 5.9, and Phi 4 costs 4.3x less per output token ($0.14 vs $0.60 per million). Updated October 21, 2026; 7 benchmarks have a result for both.
Phi 4 or Mistral Small 4: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Phi 4 for output tokens 4.3x cheaper ($0.14 vs $0.60 per million) and work measured by Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.
- Shared results
- 7
- Phi 4 only
- 39
- Mistral Small 4 only
- 8
- Like-for-like categories
- 5 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
Mistral Small 4
Mistral Small 4 leads, 11.3 against 5.9.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Mistral Small 4 has a AA Agentic Index result, 0.8.
Directional only
Long documents
Listed context window
Mistral Small 4
Mistral Small 4 takes 262K tokens against 16K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Phi 4
Phi 4 $0.0001, Mistral Small 4 $0.0004 per turn.
List prices
At a glance
- Coding index
- Phi 4 not benchmarked, Mistral Small 4 not benchmarked.
- Widest category
- Agentic work, 41.2 points apart on average over 1 shared benchmark.
- Widest single gap
- Long context reasoning (AA-LCR): Phi 4 0.0% against Mistral Small 4 49.7%, 49.7 points apart on a 0 to 100 scale.
- Output price
- Phi 4 $0.14 against Mistral Small 4 $0.60 per million output tokens, 4.3x apart.
- Context window
- Phi 4 takes 16K tokens, Mistral Small 4 262K.
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 4 | Ties |
|---|---|---|---|---|
| Coding | 0 | 1 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 2 | ||
| General | 0 | 2 | ||
| All shared boards | 0 | 7 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index01
| Benchmark | Phi 4 | Mistral Small 4 | Leader |
|---|---|---|---|
| AA Coding Index | Not measured | 26.6 | Only Mistral Small 4 measured |
| Vibe Code Bench (Vals AI) | Not measured | 0.0% | Only Mistral Small 4 measured |
| LiveCodeBench (Artificial Analysis run) | 23.1% | Not measured | Only Phi 4 measured |
| SciCode | Not measured | 38.8% | Only Mistral Small 4 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 3.8% | 17.4% | Mistral Small 4 |
| ALE-Bench | Not measured | 497.6 | Only Mistral Small 4 measured |
| LMArena Text: coding | 1231 | Not measured | Only Phi 4 measured |
| LMArena Text: software and IT | 1228 | Not measured | Only Phi 4 measured |
| Neither model has a result on the other 31 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Phi 4 | Mistral Small 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 5.9 | 11.3 | Mistral Small 4 |
| Epoch Capabilities Index | 130.5 | Not measured | Only Phi 4 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Phi 4 | Mistral Small 4 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 0.8 | Only Mistral Small 4 measured |
| τ²-Bench Telecom | 0.0% | 41.2% | Mistral Small 4 |
| BALROG | 11.6% | Not measured | Only Phi 4 measured |
| Berkeley Function Calling Leaderboard (BFCL) | 28.8% | 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 index02
| Benchmark | Phi 4 | Mistral Small 4 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 57.5% | 76.9% | Mistral Small 4 |
| Humanity's Last Exam (Artificial Analysis run) | 3.8% | 9.9% | Mistral Small 4 |
| GPQA Diamond (Epoch AI run) | 56.1% | Not measured | Only Phi 4 measured |
| LMArena Text: hard prompts | 1220 | Not measured | Only Phi 4 measured |
| LMArena Text: expert | 1203 | Not measured | Only Phi 4 measured |
| LMArena Text: hard prompts in English | 1230 | Not measured | Only Phi 4 measured |
| Kagi LLM Benchmark | Not measured | 40.5% | Only Mistral Small 4 measured |
| Neither model has a result on the other 15 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Phi 4 | Mistral Small 4 | 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 | Not measured | Only Phi 4 measured |
| LMArena Text: mathematical work | 1254 | Not measured | Only Phi 4 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Phi 4 | Mistral Small 4 | 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 | Not measured | Only Phi 4 measured |
| LMArena Text: medicine and healthcare | 1202 | Not measured | Only Phi 4 measured |
| LMArena Text: legal and government | 1241 | Not measured | Only Phi 4 measured |
| LMArena Text: business and finance | 1199 | Not measured | Only Phi 4 measured |
| Neither model has a result on the other 12 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Phi 4 | Mistral Small 4 | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Phi 4 | Mistral Small 4 | Leader |
|---|---|---|---|
| IFBench | 23.5% | 48.2% | Mistral Small 4 |
| Long context reasoning (AA-LCR) | 0.0% | 49.7% | Mistral Small 4 |
| DTBench | Not measured | 70.9% | Only Mistral Small 4 measured |
| LMCA | Not measured | 20.6% | Only Mistral Small 4 measured |
| Creative writing (Lech Mazur) | 62.6% | Not measured | Only Phi 4 measured |
| LMArena Text | 1217 | Not measured | Only Phi 4 measured |
| LMArena Text: instruction following | 1201 | Not measured | Only Phi 4 measured |
| LMArena Text: creative writing | 1181 | Not measured | Only Phi 4 measured |
| LMArena Text: English | 1231 | Not measured | Only Phi 4 measured |
| LMArena Text: non-English | 1197 | Not measured | Only Phi 4 measured |
| LMArena Text: Chinese | 1212 | Not measured | Only Phi 4 measured |
| LMArena Text: German | 1222 | Not measured | Only Phi 4 measured |
| LMArena Text: Japanese | 1158 | Not measured | Only Phi 4 measured |
| LMArena Text: Korean | 1151 | Not measured | Only Phi 4 measured |
| LMArena Text: French | 1224 | Not measured | Only Phi 4 measured |
| LMArena Text: Spanish | 1234 | Not measured | Only Phi 4 measured |
| LMArena Text: Russian | 1209 | Not measured | Only Phi 4 measured |
| LMArena Text: multi-turn | 1206 | Not measured | Only Phi 4 measured |
| LMArena Text: longer queries | 1217 | Not measured | Only Phi 4 measured |
| LMArena Text: writing and language | 1198 | Not measured | Only Phi 4 measured |
| LMArena Text: entertainment and media | 1162 | Not measured | Only Phi 4 measured |
| Neither model has a result on the other 25 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Phi 4 | Mistral Small 4 | 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 4 |
|---|---|---|
| Maker | Microsoft | Mistral AI |
| Weights | Open weights | Open weights |
| Released | January 10, 2025 | March 16, 2026 |
| Context window | 16K | 262K |
| Input $/Mtok | $0.07 | $0.15 |
| Output $/Mtok | $0.14 | $0.60 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Phi 4 better than Mistral Small 4 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Phi 4 for output tokens 4.3x cheaper ($0.14 vs $0.60 per million) and work measured by Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.
Which is cheaper, Phi 4 or Mistral Small 4?
Phi 4 costs $0.07 per million input tokens and $0.14 per million output tokens; Mistral Small 4 costs $0.15 and $0.60. Cost per solved task is known for neither of them.
Which has the bigger context window, Phi 4 or Mistral Small 4?
Mistral Small 4, with 262K tokens against 16K.
How many benchmarks is the Phi 4 vs Mistral Small 4 comparison based on?
7 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 4's on 1. Where only one model has a result, the page says so instead of naming a winner.