GPT-5.1-Codex vs Phi 4
Updated October 21, 2026. 11 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Only GPT-5.1-Codex has a coding score, 15.3 on the Vibe Coding Index; Phi 4 has none, so the two cannot be ranked on coding.
Phi 4 has the edge where output tokens cost 71.4x less.
- Shared results
- 11
- GPT-5.1-Codex only
- 15
- Phi 4 only
- 34
- Like-for-like categories
- 7 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
Only GPT-5.1-Codex has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
GPT-5.1-Codex
GPT-5.1-Codex leads, 23.7 against 5.9.
Same board, both measured
Web design
Design Arena: websites
No call
Only GPT-5.1-Codex has a Design Arena: websites result, 1162.
Directional only
Long documents
Listed context window
GPT-5.1-Codex
GPT-5.1-Codex takes 400K tokens against 16K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Phi 4
GPT-5.1-Codex $0.0063, Phi 4 $0.0001 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.1-Codex has the number, $0.892.
Directional only
At a glance
- Coding index
- GPT-5.1-Codex 15.3 from 2 benchmarks, Phi 4 not benchmarked.
- Widest category
- Agentic work, 83.0 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: GPT-5.1-Codex 83.0% against Phi 4 0.0%, 83.0 points apart on a 0 to 100 scale.
- Output price
- GPT-5.1-Codex $10.00 against Phi 4 $0.14 per million output tokens, 71.4x apart.
- Context window
- GPT-5.1-Codex takes 400K 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-5.1-Codex | Bars | Phi 4 | Ties |
|---|---|---|---|---|
| Coding | 2 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 2 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 1 | 0 | ||
| General | 2 | 0 | ||
| All shared boards | 11 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
| Benchmark | GPT-5.1-Codex | Phi 4 | Leader |
|---|---|---|---|
| SWE-bench Verified | 66.0% | Not measured | Only GPT-5.1-Codex measured |
| LMArena WebDev | 1337 | Not measured | Only GPT-5.1-Codex measured |
| LiveCodeBench (Vals AI) | 85.5% | Not measured | Only GPT-5.1-Codex measured |
| Vibe Code Bench (Vals AI) | 13.1% | Not measured | Only GPT-5.1-Codex measured |
| LiveCodeBench (Artificial Analysis run) | 84.9% | 23.1% | GPT-5.1-Codex |
| Terminal-Bench Hard (Artificial Analysis run) | 34.8% | 3.8% | GPT-5.1-Codex |
| Terminal-Bench | 57.8% | Not measured | Only GPT-5.1-Codex measured |
| ALE-Bench | 1244.9 | Not measured | Only GPT-5.1-Codex measured |
| LMArena Text: coding | Not measured | 1231 | Only Phi 4 measured |
| LMArena Text: software and IT | Not measured | 1228 | Only Phi 4 measured |
| LMArena WebDev: HTML | 1346 | Not measured | Only GPT-5.1-Codex measured |
| Neither model has a result on the other 27 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5.1-Codex | Phi 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 23.7 | 5.9 | GPT-5.1-Codex |
| Epoch Capabilities Index | Not measured | 130.5 | Only Phi 4 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5.1-Codex | Phi 4 | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1018 | Not measured | Only GPT-5.1-Codex measured |
| Design Arena: agents building full-stack apps | 1086 | Not measured | Only GPT-5.1-Codex measured |
| Design Arena: agents building mobile apps | 1191 | Not measured | Only GPT-5.1-Codex measured |
| τ²-Bench Telecom | 83.0% | 0.0% | GPT-5.1-Codex |
| BALROG | Not measured | 11.6% | Only Phi 4 measured |
| Neither model has a result on the other 34 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.1-Codex | Phi 4 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 86.0% | 57.5% | GPT-5.1-Codex |
| Humanity's Last Exam (Artificial Analysis run) | 25.7% | 3.8% | GPT-5.1-Codex |
| GPQA Diamond (Epoch AI run) | Not measured | 56.1% | Only Phi 4 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 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.1-Codex | Phi 4 | Leader |
|---|---|---|---|
| AA Math Index | 95.7 | 18.0 | GPT-5.1-Codex |
| AIME 2025 (Artificial Analysis run) | 95.7% | 18.0% | GPT-5.1-Codex |
| OTIS Mock AIME | Not measured | 13.8% | Only Phi 4 measured |
| MATH level 5 | Not measured | 64.9% | Only Phi 4 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 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5.1-Codex | Phi 4 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 86.0% | 71.4% | GPT-5.1-Codex |
| MMLU | Not measured | 84.8% | Only Phi 4 measured |
| 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 11 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | GPT-5.1-Codex | Phi 4 | Leader |
|---|---|---|---|
| Design Arena: websites | 1162 | Not measured | Only GPT-5.1-Codex measured |
| Design Arena: UI components | 1237 | Not measured | Only GPT-5.1-Codex measured |
| Design Arena: game dev | 1138 | Not measured | Only GPT-5.1-Codex measured |
| Design Arena: data viz | 1213 | Not measured | Only GPT-5.1-Codex measured |
| Design Arena: all code categories | 1152 | Not measured | Only GPT-5.1-Codex measured |
| Neither model has a result on the other 4 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.1-Codex | Phi 4 | Leader |
|---|---|---|---|
| IFBench | 70.0% | 23.5% | GPT-5.1-Codex |
| Long context reasoning (AA-LCR) | 69.3% | 0.0% | GPT-5.1-Codex |
| 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 27 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.1-Codex | 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-5.1-Codex | Microsoft Phi 4 |
|---|---|---|
| Maker | OpenAI | Microsoft |
| Weights | No public weights listed | Open weights |
| Released | November 13, 2025 | January 10, 2025 |
| Context window | 400K | 16K |
| Input $/Mtok | $1.25 | $0.07 |
| Output $/Mtok | $10.00 | $0.14 |
| Coding index | 15.3 | Not benchmarked |
| Independent measurements behind it | 2 | 0 |
| Cost per solved task | $0.892 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.1-Codex better than Phi 4 for coding?
Only GPT-5.1-Codex has a coding score, 15.3 on the Vibe Coding Index; Phi 4 has none, so the two cannot be ranked on coding. Phi 4 has the edge where output tokens cost 71.4x less.
Which is cheaper, GPT-5.1-Codex or Phi 4?
GPT-5.1-Codex costs $1.25 per million input tokens and $10.00 per million output tokens; Phi 4 costs $0.07 and $0.14. Cost per solved task is known for GPT-5.1-Codex only.
Which has the bigger context window, GPT-5.1-Codex or Phi 4?
GPT-5.1-Codex, with 400K tokens against 16K.
How many benchmarks is the GPT-5.1-Codex vs Phi 4 comparison based on?
11 benchmarks have a result for both models as of October 21, 2026. GPT-5.1-Codex's coding index rests on 2 independent benchmarks and Phi 4's on 0. Where only one model has a result, the page says so instead of naming a winner.