GPT-3.5 Turbo vs Phi 4
Phi 4 leads GPT-3.5 Turbo on the Artificial Analysis Intelligence Index, 5.9 to 5.5, and Phi 4 costs 10.7x less per output token ($0.14 vs $1.50 per million). Updated October 21, 2026; 4 benchmarks have a result for both.
GPT-3.5 Turbo or Phi 4: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick GPT-3.5 Turbo for a larger context window (16K against 16K tokens) and work measured by AA Intelligence Index or GPQA Diamond (Artificial Analysis run), where it leads.
- Shared results
- 4
- GPT-3.5 Turbo only
- 9
- Phi 4 only
- 42
- Like-for-like categories
- 3 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
Phi 4
Phi 4 leads, 5.9 against 5.5.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only GPT-3.5 Turbo has a GPQA Diamond result, 30.6%.
Directional only
Long documents
Listed context window
GPT-3.5 Turbo
GPT-3.5 Turbo takes 16K tokens against 16K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Phi 4
GPT-3.5 Turbo $0.0013, Phi 4 $0.0001 per turn.
List prices
At a glance
- Coding index
- GPT-3.5 Turbo not benchmarked, Phi 4 not benchmarked.
- Widest category
- Reasoning, 27.8 points apart on average over 1 shared benchmark.
- Widest single gap
- GPQA Diamond (Artificial Analysis run): GPT-3.5 Turbo 29.7% against Phi 4 57.5%, 27.8 points apart on a 0 to 100 scale.
- Output price
- GPT-3.5 Turbo $1.50 against Phi 4 $0.14 per million output tokens, 10.7x apart.
- Context window
- GPT-3.5 Turbo takes 16K 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-3.5 Turbo | Bars | Phi 4 | Ties |
|---|---|---|---|---|
| Intelligence | 0 | 1 | ||
| Reasoning | 0 | 1 | ||
| Knowledge | 0 | 2 | ||
| All shared boards | 0 | 4 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index6 boards, none shared
| Benchmark | GPT-3.5 Turbo | Phi 4 | Leader |
|---|---|---|---|
| AA Coding Index | 10.7 | Not measured | Only GPT-3.5 Turbo measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 23.1% | Only Phi 4 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 3.8% | Only Phi 4 measured |
| LMArena Text: coding | Not measured | 1231 | Only Phi 4 measured |
| LMArena Text: software and IT | Not measured | 1228 | Only Phi 4 measured |
| SciCode | 0.0% | Not measured | Only GPT-3.5 Turbo measured |
| Neither model has a result on the other 33 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-3.5 Turbo | Phi 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 5.5 | 5.9 | Phi 4 |
| Epoch Capabilities Index | Not measured | 130.5 | Only Phi 4 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | GPT-3.5 Turbo | Phi 4 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | Not measured | 0.0% | Only Phi 4 measured |
| BALROG | Not measured | 11.6% | Only Phi 4 measured |
| Berkeley Function Calling Leaderboard (BFCL) | Not measured | 28.8% | Only Phi 4 measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-3.5 Turbo | Phi 4 | Leader |
|---|---|---|---|
| GPQA Diamond | 30.6% | Not measured | Only GPT-3.5 Turbo measured |
| GPQA Diamond (Artificial Analysis run) | 29.7% | 57.5% | Phi 4 |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 3.8% | Only Phi 4 measured |
| GPQA Diamond (Epoch AI run) | Not measured | 56.1% | Only Phi 4 measured |
| BIG-Bench Hard | 61.6% | Not measured | Only GPT-3.5 Turbo measured |
| LMArena Text: hard prompts | Not measured | 1220 | Only Phi 4 measured |
| LMArena Text: expert | Not measured | 1203 | Only Phi 4 measured |
| LMArena Text: hard prompts in English | Not measured | 1230 | Only Phi 4 measured |
| Neither model has a result on the other 14 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | GPT-3.5 Turbo | Phi 4 | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 18.0 | Only Phi 4 measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 18.0% | Only Phi 4 measured |
| OTIS Mock AIME | Not measured | 13.8% | Only Phi 4 measured |
| MATH level 5 | Not measured | 64.9% | Only Phi 4 measured |
| GSM8K | 57.8% | Not measured | Only GPT-3.5 Turbo measured |
| LMArena Text: math | Not measured | 1246 | Only Phi 4 measured |
| LMArena Text: mathematical work | Not measured | 1254 | Only Phi 4 measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-3.5 Turbo | Phi 4 | Leader |
|---|---|---|---|
| LegalBench (Vals AI) | 64.4% | Not measured | Only GPT-3.5 Turbo measured |
| MedQA (Vals AI) | 58.5% | Not measured | Only GPT-3.5 Turbo measured |
| MMLU Pro (Artificial Analysis run) | 46.2% | 71.4% | Phi 4 |
| MMLU | 68.5% | 84.8% | Phi 4 |
| LMArena Text: science | Not measured | 1206 | Only Phi 4 measured |
| LMArena Text: medicine and healthcare | Not measured | 1202 | Only Phi 4 measured |
| LMArena Text: legal and government | Not measured | 1241 | Only Phi 4 measured |
| LMArena Text: business and finance | Not measured | 1199 | Only Phi 4 measured |
| Neither model has a result on the other 10 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-3.5 Turbo | Phi 4 | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index21 boards, none shared
| Benchmark | GPT-3.5 Turbo | Phi 4 | Leader |
|---|---|---|---|
| IFBench | Not measured | 23.5% | Only Phi 4 measured |
| Long context reasoning (AA-LCR) | Not measured | 0.0% | Only Phi 4 measured |
| DTBench | 48.5% | Not measured | Only GPT-3.5 Turbo measured |
| LMCA | 9.7% | Not measured | Only GPT-3.5 Turbo measured |
| Creative writing (Lech Mazur) | Not measured | 62.6% | Only Phi 4 measured |
| LMArena Text | Not measured | 1217 | Only Phi 4 measured |
| LMArena Text: instruction following | Not measured | 1201 | Only Phi 4 measured |
| LMArena Text: creative writing | Not measured | 1181 | Only Phi 4 measured |
| LMArena Text: English | Not measured | 1231 | Only Phi 4 measured |
| LMArena Text: non-English | Not measured | 1197 | Only Phi 4 measured |
| LMArena Text: Chinese | Not measured | 1212 | Only Phi 4 measured |
| LMArena Text: German | Not measured | 1222 | Only Phi 4 measured |
| LMArena Text: Japanese | Not measured | 1158 | Only Phi 4 measured |
| LMArena Text: Korean | Not measured | 1151 | Only Phi 4 measured |
| LMArena Text: French | Not measured | 1224 | Only Phi 4 measured |
| LMArena Text: Spanish | Not measured | 1234 | Only Phi 4 measured |
| LMArena Text: Russian | Not measured | 1209 | Only Phi 4 measured |
| LMArena Text: multi-turn | Not measured | 1206 | Only Phi 4 measured |
| LMArena Text: longer queries | Not measured | 1217 | Only Phi 4 measured |
| LMArena Text: writing and language | Not measured | 1198 | Only Phi 4 measured |
| LMArena Text: entertainment and media | Not measured | 1162 | 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 | GPT-3.5 Turbo | 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-3.5 Turbo | Microsoft Phi 4 |
|---|---|---|
| Maker | OpenAI | Microsoft |
| Weights | No public weights listed | Open weights |
| Released | May 28, 2023 | January 10, 2025 |
| Context window | 16K | 16K |
| Input $/Mtok | $0.50 | $0.07 |
| Output $/Mtok | $1.50 | $0.14 |
| 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 GPT-3.5 Turbo better than Phi 4 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-3.5 Turbo for a larger context window (16K against 16K tokens) and work measured by AA Intelligence Index or GPQA Diamond (Artificial Analysis run), where it leads.
Which is cheaper, GPT-3.5 Turbo or Phi 4?
GPT-3.5 Turbo costs $0.50 per million input tokens and $1.50 per million output tokens; Phi 4 costs $0.07 and $0.14. Cost per solved task is known for neither of them.
Which has the bigger context window, GPT-3.5 Turbo or Phi 4?
GPT-3.5 Turbo, with 16K tokens against 16K.
How many benchmarks is the GPT-3.5 Turbo vs Phi 4 comparison based on?
4 benchmarks have a result for both models as of October 21, 2026. GPT-3.5 Turbo'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.