Phi 4 vs Hy3 preview
Updated October 21, 2026. 31 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 4.3x less, and where what matters is Terminal-Bench Hard (Artificial Analysis run) or LMArena Text: coding, where it leads.
- Shared results
- 31
- Phi 4 only
- 14
- Hy3 preview only
- 5
- 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
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Hy3 preview
Hy3 preview leads, 25.3 against 5.9.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Hy3 preview has a AA Agentic Index result, 24.1.
Directional only
Long documents
Listed context window
Hy3 preview
Hy3 preview takes 262K tokens against 16K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Phi 4
Phi 4 $0.0001, Hy3 preview $0.0005 per turn.
List prices
At a glance
- Coding index
- Phi 4 not benchmarked, Hy3 preview not benchmarked.
- Widest category
- Agentic work, 92.7 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: Phi 4 0.0% against Hy3 preview 92.7%, 92.7 points apart on a 0 to 100 scale.
- Output price
- Phi 4 $0.14 against Hy3 preview $0.60 per million output tokens, 4.3x apart.
- Context window
- Phi 4 takes 16K tokens, Hy3 preview 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 | Hy3 preview | Ties |
|---|---|---|---|---|
| Coding | 0 | 3 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 5 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 4 | ||
| General | 0 | 15 | ||
| All shared boards | 0 | 31 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
| Benchmark | Phi 4 | Hy3 preview | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1357 | Only Hy3 preview measured |
| AA Coding Index | Not measured | 58.8 | Only Hy3 preview measured |
| LiveCodeBench (Artificial Analysis run) | 23.1% | Not measured | Only Phi 4 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 3.8% | 34.1% | Hy3 preview |
| LMArena Text: coding | 1231 | 1421 | Hy3 preview |
| LMArena Text: software and IT | 1228 | 1423 | Hy3 preview |
| LMArena WebDev: React | Not measured | 1349 | Only Hy3 preview measured |
| LMArena WebDev: HTML | Not measured | 1356 | Only Hy3 preview 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 | Hy3 preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 5.9 | 25.3 | Hy3 preview |
| 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 | Hy3 preview | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 24.1 | Only Hy3 preview measured |
| τ²-Bench Telecom | 0.0% | 92.7% | Hy3 preview |
| BALROG | 11.6% | Not measured | Only Phi 4 measured |
| Neither model has a result on the other 36 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Phi 4 | Hy3 preview | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 57.5% | 86.7% | Hy3 preview |
| Humanity's Last Exam (Artificial Analysis run) | 3.8% | 27.8% | Hy3 preview |
| GPQA Diamond (Epoch AI run) | 56.1% | Not measured | Only Phi 4 measured |
| LMArena Text: hard prompts | 1220 | 1413 | Hy3 preview |
| LMArena Text: expert | 1203 | 1422 | Hy3 preview |
| LMArena Text: hard prompts in English | 1230 | 1416 | Hy3 preview |
| Neither model has a result on the other 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Phi 4 | Hy3 preview | 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 | 1424 | Hy3 preview |
| LMArena Text: mathematical work | 1254 | 1442 | Hy3 preview |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Phi 4 | Hy3 preview | 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 | 1416 | Hy3 preview |
| LMArena Text: medicine and healthcare | 1202 | 1405 | Hy3 preview |
| LMArena Text: legal and government | 1241 | 1430 | Hy3 preview |
| LMArena Text: business and finance | 1199 | 1397 | Hy3 preview |
| Neither model has a result on the other 11 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Phi 4 | Hy3 preview | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index015
| Benchmark | Phi 4 | Hy3 preview | Leader |
|---|---|---|---|
| IFBench | 23.5% | 63.1% | Hy3 preview |
| Long context reasoning (AA-LCR) | 0.0% | 64.7% | Hy3 preview |
| Creative writing (Lech Mazur) | 62.6% | Not measured | Only Phi 4 measured |
| LMArena Text | 1217 | 1401 | Hy3 preview |
| LMArena Text: instruction following | 1201 | 1383 | Hy3 preview |
| LMArena Text: creative writing | 1181 | 1339 | Hy3 preview |
| LMArena Text: English | 1231 | 1409 | Hy3 preview |
| LMArena Text: non-English | 1197 | 1390 | Hy3 preview |
| LMArena Text: Chinese | 1212 | 1435 | Hy3 preview |
| 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 | 1425 | Hy3 preview |
| LMArena Text: Spanish | 1234 | 1399 | Hy3 preview |
| LMArena Text: Russian | 1209 | 1399 | Hy3 preview |
| LMArena Text: multi-turn | 1206 | 1411 | Hy3 preview |
| LMArena Text: longer queries | 1217 | 1402 | Hy3 preview |
| LMArena Text: writing and language | 1198 | 1370 | Hy3 preview |
| LMArena Text: entertainment and media | 1162 | 1352 | Hy3 preview |
| 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 | Phi 4 | Hy3 preview | 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 | Tencent Hy3 preview |
|---|---|---|
| Maker | Microsoft | Tencent |
| Weights | Open weights | Open weights |
| Released | January 10, 2025 | April 22, 2026 |
| Context window | 16K | 262K |
| Input $/Mtok | $0.07 | $0.18 |
| 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 Hy3 preview 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 4.3x less, and where what matters is Terminal-Bench Hard (Artificial Analysis run) or LMArena Text: coding, where it leads.
Which is cheaper, Phi 4 or Hy3 preview?
Phi 4 costs $0.07 per million input tokens and $0.14 per million output tokens; Hy3 preview costs $0.18 and $0.60. Cost per solved task is known for neither of them.
Which has the bigger context window, Phi 4 or Hy3 preview?
Hy3 preview, with 262K tokens against 16K.
How many benchmarks is the Phi 4 vs Hy3 preview comparison based on?
31 benchmarks have a result for both models as of October 21, 2026. Phi 4's coding index rests on 0 independent benchmarks and Hy3 preview's on 1. Where only one model has a result, the page says so instead of naming a winner.