Model comparison
Gemma 3n E4b IT vs Phi-4
Gemma 3n E4b IT is the stronger model overall, scoring 36.7 to 30.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
MicrosoftSummary
- They share 17 benchmarks with published results for both. Gemma 3n E4b IT scores higher in 8 categories and Phi-4 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 3n E4b IT leads 32.5 to 19.6.
- Gemma 3n E4b IT is cheaper at $0.06 / $0.12 per million input/output tokens, against $0.07 / $0.14 for Phi-4.
- Phi-4 accepts more context: 128K tokens versus 33K.
Side by side
| Gemma 3n E4b IT | Phi-4 | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 36.7 | 30.9 |
| Released | 2025-05-20 | 2024-12-11 |
| Weights | Open | Open |
| Context window | 33K | 128K |
| Max output | 33K | 4K |
| Input $ / M tokens | $0.06 | $0.07 |
| Output $ / M tokens | $0.12 | $0.14 |
| Results tracked | 18 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3n E4b IT leads
Gemma 3n E4b IT: 36.4 (#193), Phi-4: 33.8 (#237)
| Benchmark | Gemma 3n E4b IT | Phi-4 |
|---|---|---|
| LMArena Coding | 1269 | 1231 |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |
Agentic & Tool Use Not comparable
Gemma 3n E4b IT: —, Phi-4: 22.6 (#120)
| Benchmark | Gemma 3n E4b IT | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |
Reasoning Gemma 3n E4b IT leads
Gemma 3n E4b IT: 19.2 (#239), Phi-4: 17.0 (#287)
| Benchmark | Gemma 3n E4b IT | Phi-4 |
|---|---|---|
| LMArena Hard Prompts | 1284 | 1220 |
| Kagi LLM Benchmark | 31.5% | — |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| LiveBench Data Analysis | — | 45.2% |
| Epoch Capabilities Index | — | 130.43 |
| LiveBench | — | 41.6% |
Math Gemma 3n E4b IT leads
Gemma 3n E4b IT: 32.5 (#186), Phi-4: 19.6 (#279)
| Benchmark | Gemma 3n E4b IT | Phi-4 |
|---|---|---|
| LMArena Math | 1251 | 1246 |
| OTIS Mock AIME 2024-2025 | — | 13.8% |
| LiveBench Math | — | 42% |
| MATH Level 5 | — | 64.9% |
Knowledge Gemma 3n E4b IT leads
Gemma 3n E4b IT: 33.6 (#193), Phi-4: 32.5 (#204)
| Benchmark | Gemma 3n E4b IT | Phi-4 |
|---|---|---|
| LMArena Expert | 1245 | 1203 |
| GPQA Diamond | — | 56.1% |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| MMLU | — | 84.8% |
Multilingual Gemma 3n E4b IT leads
Gemma 3n E4b IT: 43.5 (#179), Phi-4: 37.4 (#232)
| Benchmark | Gemma 3n E4b IT | Phi-4 |
|---|---|---|
| LMArena Non-English | 1285 | 1197 |
| LMArena Chinese | 1310 | 1211 |
| LMArena French | 1330 | 1223 |
| LMArena German | 1312 | 1222 |
| LMArena Japanese | 1274 | 1158 |
| LMArena Korean | 1259 | 1151 |
| LMArena Russian | 1288 | 1209 |
| LMArena Spanish | 1305 | 1234 |
Instruction Following Gemma 3n E4b IT leads
Gemma 3n E4b IT: 66.3 (#205), Phi-4: 60.6 (#246)
| Benchmark | Gemma 3n E4b IT | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1255 | 1201 |
| LiveBench Instruction Following | — | 58.4% |
Long Context Gemma 3n E4b IT leads
Gemma 3n E4b IT: 38.8 (#185), Phi-4: 36.9 (#221)
| Benchmark | Gemma 3n E4b IT | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1277 | 1217 |
Writing & Preference Gemma 3n E4b IT leads
Gemma 3n E4b IT: 50.3 (#181), Phi-4: 40.7 (#239)
| Benchmark | Gemma 3n E4b IT | Phi-4 |
|---|---|---|
| LMArena Text | 1306 | 1217 |
| LMArena Creative Writing | 1287 | 1182 |
| LMArena Multi-Turn | 1276 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| LiveBench Language | — | 25.6% |
Frequently asked questions
Is Gemma 3n E4b IT better than Phi-4?
Gemma 3n E4b IT is the stronger model overall, scoring 36.7 to 30.9 on the Noometry Index.
Which is cheaper, Gemma 3n E4b IT or Phi-4?
Gemma 3n E4b IT is cheaper. It lists at $0.06 per million input tokens and $0.12 per million output tokens; Phi-4 lists at $0.07 and $0.14.
Is Gemma 3n E4b IT or Phi-4 better for coding?
Gemma 3n E4b IT scores higher on coding benchmarks: 36.4 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Phi-4 does, with 128K tokens against 33K.
How many benchmarks do Gemma 3n E4b IT and Phi-4 share?
17 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and Phi-4 has 37.