Gemma 4 31B vs Phi 4
Gemma 4 31B leads Phi 4 on the Artificial Analysis Intelligence Index, 14.7 to 5.9, and Phi 4 costs 2.9x less per output token ($0.14 vs $0.40 per million). Updated October 21, 2026; 34 benchmarks have a result for both.
Gemma 4 31B or Phi 4: which to pick
Only Gemma 4 31B has a coding score, 39.0 on the Vibe Coding Index; Phi 4 has none, so the two cannot be ranked on coding.
Pick Phi 4 for output tokens 2.9x cheaper ($0.14 vs $0.40 per million).
- Shared results
- 34
- Gemma 4 31B only
- 37
- Phi 4 only
- 12
- 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
Only Gemma 4 31B has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Gemma 4 31B
Gemma 4 31B leads, 14.7 against 5.9.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Gemma 4 31B has a AA Agentic Index result, 4.2.
Directional only
Long documents
Listed context window
Gemma 4 31B
Gemma 4 31B takes 262K tokens against 16K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Phi 4
Gemma 4 31B $0.0003, Phi 4 $0.0001 per turn.
List prices
At a glance
- Coding index
- Gemma 4 31B 39.0 from 2 benchmarks, Phi 4 not benchmarked.
- Widest category
- Agentic work, 65.5 points apart on average over 1 shared benchmark.
- Widest single gap
- Long context reasoning (AA-LCR): Gemma 4 31B 69.7% against Phi 4 0.0%, 69.7 points apart on a 0 to 100 scale.
- Output price
- Gemma 4 31B $0.40 against Phi 4 $0.14 per million output tokens, 2.9x apart.
- Context window
- Gemma 4 31B takes 262K 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 | Gemma 4 31B | Bars | Phi 4 | Ties |
|---|---|---|---|---|
| Coding | 3 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 6 | 0 | ||
| Math | 3 | 0 | ||
| Knowledge | 4 | 0 | ||
| General | 15 | 0 | ||
| All shared boards | 34 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
| Benchmark | Gemma 4 31B | Phi 4 | Leader |
|---|---|---|---|
| LiveBench coding | 49.0% | Not measured | Only Gemma 4 31B measured |
| LMArena WebDev | 1367 | Not measured | Only Gemma 4 31B measured |
| AA Coding Index | 43.4 | Not measured | Only Gemma 4 31B measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 23.1% | Only Phi 4 measured |
| SciCode | 45.5% | Not measured | Only Gemma 4 31B measured |
| Terminal-Bench Hard (Artificial Analysis run) | 36.4% | 3.8% | Gemma 4 31B |
| WeirdML | 52.3% | Not measured | Only Gemma 4 31B measured |
| ALE-Bench | 925.5 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: coding | 1459 | 1231 | Gemma 4 31B |
| LMArena Text: software and IT | 1463 | 1228 | Gemma 4 31B |
| LMArena WebDev: React | 1359 | Not measured | Only Gemma 4 31B measured |
| LMArena WebDev: HTML | 1380 | Not measured | Only Gemma 4 31B measured |
| SciCode | 8.9% | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 26 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Gemma 4 31B | Phi 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 14.7 | 5.9 | Gemma 4 31B |
| Epoch Capabilities Index | 143.0 | 130.5 | Gemma 4 31B |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Gemma 4 31B | Phi 4 | Leader |
|---|---|---|---|
| AA Agentic Index | 4.2 | Not measured | Only Gemma 4 31B measured |
| LiveBench research | 44.4% | Not measured | Only Gemma 4 31B measured |
| LiveBench browser | 4.0% | Not measured | Only Gemma 4 31B measured |
| LiveBench long agentic | 13.3% | Not measured | Only Gemma 4 31B measured |
| τ²-Bench Telecom | 65.5% | 0.0% | Gemma 4 31B |
| 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 34 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Gemma 4 31B | Phi 4 | Leader |
|---|---|---|---|
| LiveBench reasoning | 68.3% | Not measured | Only Gemma 4 31B measured |
| GPQA Diamond (Artificial Analysis run) | 85.7% | 57.5% | Gemma 4 31B |
| Humanity's Last Exam (Artificial Analysis run) | 23.6% | 3.8% | Gemma 4 31B |
| GPQA Diamond (Epoch AI run) | 75.8% | 56.1% | Gemma 4 31B |
| LMArena Text: hard prompts | 1448 | 1220 | Gemma 4 31B |
| LMArena Text: expert | 1464 | 1203 | Gemma 4 31B |
| LMArena Text: hard prompts in English | 1456 | 1230 | Gemma 4 31B |
| LMArena Vision: diagrams | 1283 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: homework | 1310 | Not measured | Only Gemma 4 31B measured |
| Kagi LLM Benchmark | 63.5% | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 12 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Gemma 4 31B | 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 | 73.3% | 13.8% | Gemma 4 31B |
| MATH level 5 | Not measured | 64.9% | Only Phi 4 measured |
| LMArena Text: math | 1463 | 1246 | Gemma 4 31B |
| LMArena Text: mathematical work | 1465 | 1254 | Gemma 4 31B |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Gemma 4 31B | Phi 4 | Leader |
|---|---|---|---|
| CaseLaw (Vals AI) | 52.6% | Not measured | Only Gemma 4 31B measured |
| MortgageTax (Vals AI) | 61.4% | Not measured | Only Gemma 4 31B measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 71.4% | Only Phi 4 measured |
| SimpleQA Verified | 10.4% | Not measured | Only Gemma 4 31B measured |
| MMLU | Not measured | 84.8% | Only Phi 4 measured |
| LMArena Text: science | 1457 | 1206 | Gemma 4 31B |
| LMArena Text: medicine and healthcare | 1451 | 1202 | Gemma 4 31B |
| LMArena Text: legal and government | 1438 | 1241 | Gemma 4 31B |
| LMArena Text: business and finance | 1430 | 1199 | Gemma 4 31B |
| FACTS Benchmark Suite | 45.3% | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 8 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Gemma 4 31B | Phi 4 | Leader |
|---|---|---|---|
| LiveBench design | 58.4% | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 8 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index150
| Benchmark | Gemma 4 31B | Phi 4 | Leader |
|---|---|---|---|
| LiveBench data analysis | 53.3% | Not measured | Only Gemma 4 31B measured |
| SAGE (Vals AI) | 55.0% | Not measured | Only Gemma 4 31B measured |
| IFBench | 75.6% | 23.5% | Gemma 4 31B |
| Long context reasoning (AA-LCR) | 69.7% | 0.0% | Gemma 4 31B |
| DTBench | 82.7% | Not measured | Only Gemma 4 31B measured |
| LMCA | 39.3% | Not measured | Only Gemma 4 31B measured |
| Creative writing (Lech Mazur) | Not measured | 62.6% | Only Phi 4 measured |
| Surface Evolver Bench | 30.6% | Not measured | Only Gemma 4 31B measured |
| LMArena Text | 1443 | 1217 | Gemma 4 31B |
| LMArena Text: instruction following | 1433 | 1201 | Gemma 4 31B |
| LMArena Text: creative writing | 1417 | 1181 | Gemma 4 31B |
| LMArena Vision | 1276 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: English | 1451 | 1231 | Gemma 4 31B |
| LMArena Text: non-English | 1430 | 1197 | Gemma 4 31B |
| LMArena Text: Chinese | 1475 | 1212 | Gemma 4 31B |
| 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 | 1436 | 1224 | Gemma 4 31B |
| LMArena Text: Spanish | 1442 | 1234 | Gemma 4 31B |
| LMArena Text: Russian | 1460 | 1209 | Gemma 4 31B |
| LMArena Text: Polish | 1433 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: multi-turn | 1452 | 1206 | Gemma 4 31B |
| LMArena Text: longer queries | 1446 | 1217 | Gemma 4 31B |
| LMArena Text: writing and language | 1432 | 1198 | Gemma 4 31B |
| LMArena Text: entertainment and media | 1405 | 1162 | Gemma 4 31B |
| LMArena Vision: English | 1271 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: Chinese | 1326 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: reading text | 1282 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: humor | 1280 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: captioning | 1218 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: recognizing things | 1226 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: creative writing | 1285 | Not measured | Only Gemma 4 31B measured |
| LMArena Document | 1425 | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 12 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemma 4 31B | 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 | Google Gemma 4 31B | Microsoft Phi 4 |
|---|---|---|
| Maker | Microsoft | |
| Weights | Open weights | Open weights |
| Released | April 2, 2026 | January 10, 2025 |
| Context window | 262K | 16K |
| Input $/Mtok | $0.14 | $0.07 |
| Output $/Mtok | $0.40 | $0.14 |
| Coding index | 39.0 | Not benchmarked |
| Independent measurements behind it | 2 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemma 4 31B better than Phi 4 for coding?
Only Gemma 4 31B has a coding score, 39.0 on the Vibe Coding Index; Phi 4 has none, so the two cannot be ranked on coding. Pick Phi 4 for output tokens 2.9x cheaper ($0.14 vs $0.40 per million).
Which is cheaper, Gemma 4 31B or Phi 4?
Gemma 4 31B costs $0.14 per million input tokens and $0.40 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, Gemma 4 31B or Phi 4?
Gemma 4 31B, with 262K tokens against 16K.
How many benchmarks is the Gemma 4 31B vs Phi 4 comparison based on?
34 benchmarks have a result for both models as of October 21, 2026. Gemma 4 31B'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.