GPT-4.1 vs Phi 4
GPT-4.1 leads Phi 4 on the Artificial Analysis Intelligence Index, 12.7 to 5.9, and Phi 4 costs 57.1x less per output token ($0.14 vs $8.00 per million). Updated October 21, 2026; 42 benchmarks have a result for both.
GPT-4.1 or Phi 4: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick GPT-4.1 for a larger context window (1.05M against 16K tokens).
- Shared results
- 42
- GPT-4.1 only
- 45
- Phi 4 only
- 3
- Like-for-like categories
- 7 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
GPT-4.1
GPT-4.1 leads, 12.7 against 5.9.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only GPT-4.1 has a GPQA Diamond result, 65.4%.
Directional only
Math
AIME
No call
Only GPT-4.1 has a AIME result, 39.6%.
Directional only
Knowledge
MMLU Pro
No call
Only GPT-4.1 has a MMLU Pro result, 80.5%.
Directional only
Web design
Design Arena: websites
No call
Only GPT-4.1 has a Design Arena: websites result, 1039.
Directional only
Long documents
Listed context window
GPT-4.1
GPT-4.1 takes 1.05M tokens against 16K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Phi 4
GPT-4.1 $0.0060, Phi 4 $0.0001 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-4.1 has the number, $0.37.
Directional only
At a glance
- Coding index
- GPT-4.1 not benchmarked, Phi 4 not benchmarked.
- Widest category
- Agentic work, 47.1 points apart on average over 1 shared benchmark.
- Widest single gap
- Long context reasoning (AA-LCR): GPT-4.1 68.3% against Phi 4 0.0%, 68.3 points apart on a 0 to 100 scale.
- Output price
- GPT-4.1 $8.00 against Phi 4 $0.14 per million output tokens, 57.1x apart.
- Context window
- GPT-4.1 takes 1.05M tokens, Phi 4 16K.
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 | GPT-4.1 | Bars | Phi 4 | Ties |
|---|---|---|---|---|
| Coding | 4 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 6 | 0 | ||
| Math | 6 | 0 | ||
| Knowledge | 5 | 0 | ||
| General | 18 | 0 | ||
| All shared boards | 42 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
| Benchmark | GPT-4.1 | Phi 4 | Leader |
|---|---|---|---|
| Aider polyglot | 52.4% | Not measured | Only GPT-4.1 measured |
| SWE-bench Verified | 39.6% | Not measured | Only GPT-4.1 measured |
| SWE-bench Multimodal | 31.1% | Not measured | Only GPT-4.1 measured |
| LiveCodeBench (Vals AI) | 54.7% | Not measured | Only GPT-4.1 measured |
| LiveCodeBench (Artificial Analysis run) | 45.7% | 23.1% | GPT-4.1 |
| Terminal-Bench Hard (Artificial Analysis run) | 13.6% | 3.8% | GPT-4.1 |
| WeirdML | 39.0% | Not measured | Only GPT-4.1 measured |
| ALE-Bench | 558.1 | Not measured | Only GPT-4.1 measured |
| LMArena Text: coding | 1390 | 1231 | GPT-4.1 |
| LMArena Text: software and IT | 1391 | 1228 | GPT-4.1 |
| Neither model has a result on the other 28 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-4.1 | Phi 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 12.7 | 5.9 | GPT-4.1 |
| Epoch Capabilities Index | 136.7 | 130.5 | GPT-4.1 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-4.1 | Phi 4 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 47.1% | 0.0% | GPT-4.1 |
| BALROG | Not measured | 11.6% | 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 index60
| Benchmark | GPT-4.1 | Phi 4 | Leader |
|---|---|---|---|
| GPQA Diamond | 65.4% | Not measured | Only GPT-4.1 measured |
| MMMU Pro (Vals AI) | 72.4% | Not measured | Only GPT-4.1 measured |
| GPQA Diamond (Artificial Analysis run) | 66.6% | 57.5% | GPT-4.1 |
| Humanity's Last Exam (Artificial Analysis run) | 4.2% | 3.8% | GPT-4.1 |
| GPQA Diamond (Epoch AI run) | 66.9% | 56.1% | GPT-4.1 |
| ARC-AGI | 5.5% | Not measured | Only GPT-4.1 measured |
| ARC-AGI-2 | 0.4% | Not measured | Only GPT-4.1 measured |
| SimpleBench | 27.0% | Not measured | Only GPT-4.1 measured |
| Chess puzzles | 3.0% | Not measured | Only GPT-4.1 measured |
| LMArena Text: hard prompts | 1384 | 1220 | GPT-4.1 |
| LMArena Text: expert | 1364 | 1203 | GPT-4.1 |
| LMArena Text: hard prompts in English | 1393 | 1230 | GPT-4.1 |
| LMArena Vision: diagrams | 1215 | Not measured | Only GPT-4.1 measured |
| LMArena Vision: homework | 1248 | Not measured | Only GPT-4.1 measured |
| Neither model has a result on the other 7 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | GPT-4.1 | Phi 4 | Leader |
|---|---|---|---|
| AIME | 39.6% | Not measured | Only GPT-4.1 measured |
| MATH 500 (Vals AI) | 87.2% | Not measured | Only GPT-4.1 measured |
| MGSM (Vals AI) | 87.7% | Not measured | Only GPT-4.1 measured |
| AA Math Index | 34.7 | 18.0 | GPT-4.1 |
| AIME 2025 (Artificial Analysis run) | 34.7% | 18.0% | GPT-4.1 |
| OTIS Mock AIME | 38.3% | 13.8% | GPT-4.1 |
| FrontierMath, tiers 1 to 3 | 6.0% | Not measured | Only GPT-4.1 measured |
| MATH level 5 | 83.0% | 64.9% | GPT-4.1 |
| LMArena Text: math | 1369 | 1246 | GPT-4.1 |
| LMArena Text: mathematical work | 1360 | 1254 | GPT-4.1 |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | GPT-4.1 | Phi 4 | Leader |
|---|---|---|---|
| MMLU Pro | 80.5% | Not measured | Only GPT-4.1 measured |
| LegalBench (Vals AI) | 83.1% | Not measured | Only GPT-4.1 measured |
| CaseLaw (Vals AI) | 69.9% | Not measured | Only GPT-4.1 measured |
| CorpFin (Vals AI) | 63.0% | Not measured | Only GPT-4.1 measured |
| TaxEval (Vals AI) | 75.1% | Not measured | Only GPT-4.1 measured |
| MortgageTax (Vals AI) | 65.9% | Not measured | Only GPT-4.1 measured |
| MedQA (Vals AI) | 91.2% | Not measured | Only GPT-4.1 measured |
| MMLU Pro (Artificial Analysis run) | 80.6% | 71.4% | GPT-4.1 |
| SimpleQA Verified | 31.1% | Not measured | Only GPT-4.1 measured |
| MMLU | Not measured | 84.8% | Only Phi 4 measured |
| GeoBench | 72.0% | Not measured | Only GPT-4.1 measured |
| LMArena Text: science | 1382 | 1206 | GPT-4.1 |
| LMArena Text: medicine and healthcare | 1379 | 1202 | GPT-4.1 |
| LMArena Text: legal and government | 1399 | 1241 | GPT-4.1 |
| LMArena Text: business and finance | 1369 | 1199 | GPT-4.1 |
| Neither model has a result on the other 2 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | GPT-4.1 | Phi 4 | Leader |
|---|---|---|---|
| Design Arena: websites | 1039 | Not measured | Only GPT-4.1 measured |
| Design Arena: UI components | 1000 | Not measured | Only GPT-4.1 measured |
| Design Arena: game dev | 1080 | Not measured | Only GPT-4.1 measured |
| Design Arena: data viz | 1104 | Not measured | Only GPT-4.1 measured |
| Design Arena: 3D | 850 | Not measured | Only GPT-4.1 measured |
| Design Arena: all code categories | 1026 | Not measured | Only GPT-4.1 measured |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index180
| Benchmark | GPT-4.1 | Phi 4 | Leader |
|---|---|---|---|
| IFBench | 43.0% | 23.5% | GPT-4.1 |
| Long context reasoning (AA-LCR) | 68.3% | 0.0% | GPT-4.1 |
| DTBench | 68.3% | Not measured | Only GPT-4.1 measured |
| LMCA | 25.6% | Not measured | Only GPT-4.1 measured |
| Fiction.LiveBench | 63.9% | Not measured | Only GPT-4.1 measured |
| Creative writing (Lech Mazur) | Not measured | 62.6% | Only Phi 4 measured |
| LMArena Text | 1383 | 1217 | GPT-4.1 |
| LMArena Text: instruction following | 1367 | 1201 | GPT-4.1 |
| LMArena Text: creative writing | 1363 | 1181 | GPT-4.1 |
| LMArena Vision | 1210 | Not measured | Only GPT-4.1 measured |
| LMArena Text: English | 1392 | 1231 | GPT-4.1 |
| LMArena Text: non-English | 1370 | 1197 | GPT-4.1 |
| LMArena Text: Chinese | 1382 | 1212 | GPT-4.1 |
| LMArena Text: German | 1381 | 1222 | GPT-4.1 |
| LMArena Text: Japanese | 1319 | 1158 | GPT-4.1 |
| LMArena Text: Korean | 1338 | 1151 | GPT-4.1 |
| LMArena Text: French | 1382 | 1224 | GPT-4.1 |
| LMArena Text: Spanish | 1376 | 1234 | GPT-4.1 |
| LMArena Text: Russian | 1377 | 1209 | GPT-4.1 |
| LMArena Text: Polish | 1389 | Not measured | Only GPT-4.1 measured |
| LMArena Text: multi-turn | 1397 | 1206 | GPT-4.1 |
| LMArena Text: longer queries | 1385 | 1217 | GPT-4.1 |
| LMArena Text: writing and language | 1371 | 1198 | GPT-4.1 |
| LMArena Text: entertainment and media | 1365 | 1162 | GPT-4.1 |
| LMArena Vision: English | 1209 | Not measured | Only GPT-4.1 measured |
| LMArena Vision: Chinese | 1226 | Not measured | Only GPT-4.1 measured |
| LMArena Vision: reading text | 1218 | Not measured | Only GPT-4.1 measured |
| LMArena Vision: humor | 1196 | Not measured | Only GPT-4.1 measured |
| LMArena Vision: captioning | 1207 | Not measured | Only GPT-4.1 measured |
| LMArena Vision: recognizing things | 1208 | Not measured | Only GPT-4.1 measured |
| LMArena Vision: creative writing | 1210 | Not measured | Only GPT-4.1 measured |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4.1 | Phi 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 | OpenAI GPT-4.1 | Microsoft Phi 4 |
|---|---|---|
| Maker | OpenAI | Microsoft |
| Weights | No public weights listed | Open weights |
| Released | April 14, 2025 | January 10, 2025 |
| Context window | 1.05M | 16K |
| Input $/Mtok | $2.00 | $0.07 |
| Output $/Mtok | $8.00 | $0.14 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | $0.37 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-4.1 better than Phi 4 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4.1 for a larger context window (1.05M against 16K tokens).
Which is cheaper, GPT-4.1 or Phi 4?
GPT-4.1 costs $2.00 per million input tokens and $8.00 per million output tokens; Phi 4 costs $0.07 and $0.14. Cost per solved task is known for GPT-4.1 only.
Which has the bigger context window, GPT-4.1 or Phi 4?
GPT-4.1, with 1.05M tokens against 16K.
How many benchmarks is the GPT-4.1 vs Phi 4 comparison based on?
42 benchmarks have a result for both models as of October 21, 2026. GPT-4.1's coding index rests on 0 independent benchmarks and Phi 4's on 0. Where only one model has a result, the page says so instead of naming a winner.