Model comparison
Gemma 4 31B IT vs phi-3-medium 14B
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 29.7 on the Noometry Index.
Last verified . 2 shared benchmarks.
Google
MicrosoftSummary
- They share 2 benchmarks with published results for both. Gemma 4 31B IT scores higher in 3 categories and phi-3-medium 14B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 4 31B IT leads 37.9 to 9.1.
- The biggest single-benchmark swing is GPQA Diamond: 75.8% for Gemma 4 31B IT and 27.6% for phi-3-medium 14B.
Side by side
| Gemma 4 31B IT | phi-3-medium 14B | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 43.5 | 29.7 |
| Released | 2026-04-02 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.09 | — |
| Output $ / M tokens | $0.34 | — |
| Results tracked | 35 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Gemma 4 31B IT: 42.3 (#108), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Gemma 4 31B IT | phi-3-medium 14B |
|---|---|---|
| LMArena WebDev | 1366 | — |
| SciCode | 43.4% | — |
| WeirdML | 52.3% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1459 | — |
| BigCodeBench Complete | — | 48.7% |
| ALE-Bench | 925.5 | — |
Reasoning Not comparable
Gemma 4 31B IT: 27.2 (#122), phi-3-medium 14B: —
| Benchmark | Gemma 4 31B IT | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 142.74 | 121.23 |
| Kagi LLM Benchmark | 63.5% | — |
| NYT Connections (extended) | 70.6% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| LMArena Hard Prompts | 1448 | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 43.2 (#81), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Gemma 4 31B IT | phi-3-medium 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | — |
| LMArena Math | 1465 | — |
| MATH Level 5 | — | 17.6% |
Knowledge Gemma 4 31B IT leads
Gemma 4 31B IT: 37.9 (#151), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Gemma 4 31B IT | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 75.8% | 27.6% |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |
| LMArena Expert | 1465 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multimodal Not comparable
Gemma 4 31B IT: 41.6 (#34), phi-3-medium 14B: —
| Benchmark | Gemma 4 31B IT | phi-3-medium 14B |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |
Multilingual Not comparable
Gemma 4 31B IT: 53.8 (#57), phi-3-medium 14B: —
| Benchmark | Gemma 4 31B IT | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1431 | — |
| LMArena Chinese | 1476 | — |
| LMArena French | 1435 | — |
| LMArena Russian | 1460 | — |
| LMArena Spanish | 1444 | — |
Instruction Following Not comparable
Gemma 4 31B IT: 75.5 (#61), phi-3-medium 14B: —
| Benchmark | Gemma 4 31B IT | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1433 | — |
Long Context Not comparable
Gemma 4 31B IT: 44.2 (#71), phi-3-medium 14B: —
| Benchmark | Gemma 4 31B IT | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1446 | — |
Writing & Preference Not comparable
Gemma 4 31B IT: 60.5 (#96), phi-3-medium 14B: —
| Benchmark | Gemma 4 31B IT | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1443 | — |
| LMArena Creative Writing | 1415 | — |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
| LMArena Multi-Turn | 1452 | — |
Frequently asked questions
Is Gemma 4 31B IT better than phi-3-medium 14B?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 29.7 on the Noometry Index.
Is Gemma 4 31B IT or phi-3-medium 14B better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 36.8 in the Noometry coding category.
How many benchmarks do Gemma 4 31B IT and phi-3-medium 14B share?
2 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and phi-3-medium 14B has 13.