Model comparison
Gemma 1.1 2b IT vs Phi-4
Phi-4 is the stronger model overall, scoring 31.2 to 29.3 on the Noometry Index.
Last verified . 14 shared benchmarks.
Google
MicrosoftSummary
- They share 14 benchmarks with published results for both. Gemma 1.1 2b IT scores higher in 2 categories and Phi-4 in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Phi-4 leads 40.5 to 25.1.
Side by side
| Gemma 1.1 2b IT | Phi-4 | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 29.3 | 31.2 |
| Released | — | 2024-12-11 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.07 |
| Output $ / M tokens | — | $0.14 |
| Results tracked | 16 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi-4 leads
Gemma 1.1 2b IT: 30.1 (#299), Phi-4: 34.4 (#239)
| Benchmark | Gemma 1.1 2b IT | Phi-4 |
|---|---|---|
| LMArena Coding | 1034 | 1231 |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |
| HumanEval+ | 17.7% | — |
| MBPP+ | 23.3% | — |
Agentic & Tool Use Not comparable
Gemma 1.1 2b IT: —, Phi-4: 22.8 (#128)
| Benchmark | Gemma 1.1 2b IT | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |
Reasoning Gemma 1.1 2b IT leads
Gemma 1.1 2b IT: 19.1 (#270), Phi-4: 17.7 (#291)
| Benchmark | Gemma 1.1 2b IT | Phi-4 |
|---|---|---|
| LMArena Hard Prompts | 1005 | 1220 |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| LiveBench Data Analysis | — | 45.2% |
| Epoch Capabilities Index | — | 130.42 |
| LiveBench | — | 41.6% |
Math Gemma 1.1 2b IT leads
Gemma 1.1 2b IT: 30.8 (#232), Phi-4: 20.8 (#285)
| Benchmark | Gemma 1.1 2b IT | Phi-4 |
|---|---|---|
| LMArena Math | 1047 | 1246 |
| OTIS Mock AIME 2024-2025 | — | 13.8% |
| LiveBench Math | — | 42% |
| MATH Level 5 | — | 64.9% |
Knowledge Phi-4 leads
Gemma 1.1 2b IT: 26.5 (#258), Phi-4: 32.6 (#209)
| Benchmark | Gemma 1.1 2b IT | Phi-4 |
|---|---|---|
| LMArena Expert | 970 | 1203 |
| GPQA Diamond | — | 56.1% |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| MMLU | — | 84.8% |
Multilingual Phi-4 leads
Gemma 1.1 2b IT: 24.6 (#289), Phi-4: 37.2 (#237)
| Benchmark | Gemma 1.1 2b IT | Phi-4 |
|---|---|---|
| LMArena Non-English | 988 | 1197 |
| LMArena Chinese | 1012 | 1212 |
| LMArena German | 944 | 1222 |
| LMArena Korean | 899 | 1151 |
| LMArena Russian | 990 | 1209 |
| LMArena French | — | 1224 |
| LMArena Japanese | — | 1158 |
| LMArena Spanish | — | 1234 |
Instruction Following Phi-4 leads
Gemma 1.1 2b IT: 49.9 (#299), Phi-4: 60.4 (#251)
| Benchmark | Gemma 1.1 2b IT | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 992 | 1201 |
| LiveBench Instruction Following | — | 58.4% |
Long Context Phi-4 leads
Gemma 1.1 2b IT: 30.6 (#286), Phi-4: 36.9 (#226)
| Benchmark | Gemma 1.1 2b IT | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1003 | 1217 |
Writing & Preference Phi-4 leads
Gemma 1.1 2b IT: 25.1 (#306), Phi-4: 40.5 (#244)
| Benchmark | Gemma 1.1 2b IT | Phi-4 |
|---|---|---|
| LMArena Text | 1022 | 1217 |
| LMArena Creative Writing | 998 | 1182 |
| LMArena Multi-Turn | 959 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| LiveBench Language | — | 25.6% |
Frequently asked questions
Is Gemma 1.1 2b IT better than Phi-4?
Phi-4 is the stronger model overall, scoring 31.2 to 29.3 on the Noometry Index.
Is Gemma 1.1 2b IT or Phi-4 better for coding?
Phi-4 scores higher on coding benchmarks: 34.4 versus 30.1 in the Noometry coding category.
How many benchmarks do Gemma 1.1 2b IT and Phi-4 share?
14 benchmarks have published results for both models. Gemma 1.1 2b IT has 16 scored results on Noometry and Phi-4 has 37.