Phi 4 vs Mistral Large 3 2512
Updated October 21, 2026. 1 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 10.7x less, and where the benchmark that matters is AA Intelligence Index, where it leads.
- Shared results
- 1
- Phi 4 only
- 44
- Mistral Large 3 2512 only
- 27
- Like-for-like categories
- 1 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
Mistral Large 3 2512
Mistral Large 3 2512 leads, 9.3 against 5.9.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Mistral Large 3 2512 has a AA Agentic Index result, 1.0.
Directional only
Reasoning
GPQA Diamond
No call
Only Mistral Large 3 2512 has a GPQA Diamond result, 68.4%.
Directional only
Math
AIME
No call
Only Mistral Large 3 2512 has a AIME result, 42.9%.
Directional only
Knowledge
MMLU Pro
No call
Only Mistral Large 3 2512 has a MMLU Pro result, 79.8%.
Directional only
Web design
Design Arena: websites
No call
Only Mistral Large 3 2512 has a Design Arena: websites result, 1162.
Directional only
Long documents
Listed context window
Mistral Large 3 2512
Mistral Large 3 2512 takes 262K tokens against 16K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Phi 4
Phi 4 $0.0001, Mistral Large 3 2512 $0.0013 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Mistral Large 3 2512 has the number, $0.77.
Directional only
At a glance
- Coding index
- Phi 4 not benchmarked, Mistral Large 3 2512 not benchmarked.
- Widest category
- Intelligence, 3.4 points apart on average over 1 shared benchmark.
- Widest single gap
- AA Intelligence Index: Phi 4 5.9 against Mistral Large 3 2512 9.3, 3.4 points apart on a 0 to 100 scale.
- Output price
- Phi 4 $0.14 against Mistral Large 3 2512 $1.50 per million output tokens, 10.7x apart.
- Context window
- Phi 4 takes 16K tokens, Mistral Large 3 2512 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 Large 3 2512 | Ties |
|---|---|---|---|---|
| Intelligence | 0 | 1 | ||
| All shared boards | 0 | 1 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index8 boards, none shared
| Benchmark | Phi 4 | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| AA Coding Index | Not measured | 20.1 | Only Mistral Large 3 2512 measured |
| LiveCodeBench (Vals AI) | Not measured | 55.3% | Only Mistral Large 3 2512 measured |
| SWE-bench Verified (Vals AI) | Not measured | 41.4% | Only Mistral Large 3 2512 measured |
| 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 |
| ALE-Bench | Not measured | 264.7 | Only Mistral Large 3 2512 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 30 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Phi 4 | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| AA Intelligence Index | 5.9 | 9.3 | Mistral Large 3 2512 |
| Epoch Capabilities Index | 130.5 | Not measured | Only Phi 4 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Phi 4 | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 1.0 | Only Mistral Large 3 2512 measured |
| 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 36 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Phi 4 | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 68.4% | Only Mistral Large 3 2512 measured |
| MMMU Pro (Vals AI) | Not measured | 66.2% | Only Mistral Large 3 2512 measured |
| 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 | 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 |
| Neither model has a result on the other 13 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Phi 4 | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| AIME | Not measured | 42.9% | Only Mistral Large 3 2512 measured |
| MGSM (Vals AI) | Not measured | 85.4% | Only Mistral Large 3 2512 measured |
| 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 5 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index13 boards, none shared
| Benchmark | Phi 4 | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 79.8% | Only Mistral Large 3 2512 measured |
| LegalBench (Vals AI) | Not measured | 79.1% | Only Mistral Large 3 2512 measured |
| CaseLaw (Vals AI) | Not measured | 61.4% | Only Mistral Large 3 2512 measured |
| CorpFin (Vals AI) | Not measured | 61.0% | Only Mistral Large 3 2512 measured |
| TaxEval (Vals AI) | Not measured | 73.1% | Only Mistral Large 3 2512 measured |
| MortgageTax (Vals AI) | Not measured | 52.1% | Only Mistral Large 3 2512 measured |
| MedQA (Vals AI) | Not measured | 82.2% | Only Mistral Large 3 2512 measured |
| 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 4 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Phi 4 | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1162 | Only Mistral Large 3 2512 measured |
| Design Arena: UI components | Not measured | 1102 | Only Mistral Large 3 2512 measured |
| Design Arena: game dev | Not measured | 1080 | Only Mistral Large 3 2512 measured |
| Design Arena: data viz | Not measured | 1136 | Only Mistral Large 3 2512 measured |
| Design Arena: 3D | Not measured | 1099 | Only Mistral Large 3 2512 measured |
| Design Arena: all code categories | Not measured | 1142 | Only Mistral Large 3 2512 measured |
| Design Arena: SVG | Not measured | 993 | Only Mistral Large 3 2512 measured |
| Design Arena: ASCII art | Not measured | 1069 | Only Mistral Large 3 2512 measured |
| Neither model has a result on the other 1 board here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index22 boards, none shared
| Benchmark | Phi 4 | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 24.6% | Only Mistral Large 3 2512 measured |
| IFBench | 23.5% | Not measured | Only Phi 4 measured |
| Long context reasoning (AA-LCR) | 0.0% | Not measured | Only Phi 4 measured |
| DTBench | Not measured | 65.1% | Only Mistral Large 3 2512 measured |
| LMCA | Not measured | 16.7% | Only Mistral Large 3 2512 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 24 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Phi 4 | Mistral Large 3 2512 | 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 Large 3 2512 |
|---|---|---|
| Maker | Microsoft | Mistral AI |
| Weights | Open weights | No public weights listed |
| Released | January 10, 2025 | December 1, 2025 |
| Context window | 16K | 262K |
| Input $/Mtok | $0.07 | $0.50 |
| Output $/Mtok | $0.14 | $1.50 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 1 |
| Cost per solved task | Not computable | $0.77 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Phi 4 better than Mistral Large 3 2512 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 10.7x less, and where the benchmark that matters is AA Intelligence Index, where it leads.
Which is cheaper, Phi 4 or Mistral Large 3 2512?
Phi 4 costs $0.07 per million input tokens and $0.14 per million output tokens; Mistral Large 3 2512 costs $0.50 and $1.50. Cost per solved task is known for Mistral Large 3 2512 only.
Which has the bigger context window, Phi 4 or Mistral Large 3 2512?
Mistral Large 3 2512, with 262K tokens against 16K.
How many benchmarks is the Phi 4 vs Mistral Large 3 2512 comparison based on?
1 benchmarks have a result for both models as of October 21, 2026. Phi 4's coding index rests on 0 independent benchmarks and Mistral Large 3 2512's on 1. Where only one model has a result, the page says so instead of naming a winner.