Model comparison
Gemma 2 2b IT vs Gemma 3 4B
Gemma 2 2b IT is the stronger model overall, scoring 33.1 to 28.1 on the Noometry Index.
Last verified . 12 shared benchmarks.
GoogleSummary
- They share 12 benchmarks with published results for both. Gemma 2 2b IT scores higher in 3 categories and Gemma 3 4B in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 2 2b IT leads 29.9 to 11.8.
Side by side
| Gemma 2 2b IT | Gemma 3 4B | |
|---|---|---|
| Provider | ||
| Noometry Index | 33.1 | 28.1 |
| Released | — | 2025-03-12 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.04 |
| Output $ / M tokens | — | $0.08 |
| Results tracked | 17 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 4B leads
Gemma 2 2b IT: 32.3 (#273), Gemma 3 4B: 35.9 (#215)
| Benchmark | Gemma 2 2b IT | Gemma 3 4B |
|---|---|---|
| LMArena Coding | 1112 | 1230 |
Agentic & Tool Use Not comparable
Gemma 2 2b IT: —, Gemma 3 4B: 20.9 (#142)
| Benchmark | Gemma 2 2b IT | Gemma 3 4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 19.6% |
Reasoning Gemma 2 2b IT leads
Gemma 2 2b IT: 21.4 (#224), Gemma 3 4B: 13.2 (#335)
| Benchmark | Gemma 2 2b IT | Gemma 3 4B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1253 |
| Kagi LLM Benchmark | — | 25.2% |
| Chess Puzzles | — | 0% |
| DTBench | — | 50.9% |
| LMCA | — | 2.8% |
| Epoch Capabilities Index | — | 116.02 |
Math Gemma 2 2b IT leads
Gemma 2 2b IT: 32.6 (#212), Gemma 3 4B: 16.8 (#292)
| Benchmark | Gemma 2 2b IT | Gemma 3 4B |
|---|---|---|
| LMArena Math | 1135 | 1239 |
| OTIS Mock AIME 2024-2025 | — | 7.5% |
Knowledge Gemma 2 2b IT leads
Gemma 2 2b IT: 29.9 (#231), Gemma 3 4B: 11.8 (#299)
| Benchmark | Gemma 2 2b IT | Gemma 3 4B |
|---|---|---|
| LMArena Expert | 1096 | 1223 |
| GPQA Diamond | — | 23.2% |
| Vectara Hallucination Rate | — | 6.4% |
Multilingual Gemma 3 4B leads
Gemma 2 2b IT: 32.3 (#257), Gemma 3 4B: 42.5 (#194)
| Benchmark | Gemma 2 2b IT | Gemma 3 4B |
|---|---|---|
| LMArena Non-English | 1121 | 1273 |
| LMArena German | 1114 | 1281 |
| LMArena Russian | 1118 | 1294 |
| LMArena Chinese | 1132 | — |
| LMArena French | 1157 | — |
| LMArena Japanese | 1083 | — |
| LMArena Korean | 1055 | — |
| LMArena Spanish | 1140 | — |
Instruction Following Gemma 3 4B leads
Gemma 2 2b IT: 57.8 (#263), Gemma 3 4B: 65.2 (#225)
| Benchmark | Gemma 2 2b IT | Gemma 3 4B |
|---|---|---|
| LMArena Instruction Following | 1118 | 1239 |
Long Context Gemma 3 4B leads
Gemma 2 2b IT: 34.3 (#250), Gemma 3 4B: 38.7 (#194)
| Benchmark | Gemma 2 2b IT | Gemma 3 4B |
|---|---|---|
| LMArena Longer Query | 1130 | 1273 |
Writing & Preference Gemma 3 4B leads
Gemma 2 2b IT: 36.5 (#263), Gemma 3 4B: 42.0 (#239)
| Benchmark | Gemma 2 2b IT | Gemma 3 4B |
|---|---|---|
| LMArena Text | 1156 | 1291 |
| LMArena Creative Writing | 1147 | 1271 |
| LMArena Multi-Turn | 1118 | 1255 |
| EQ-Bench Creative Writing | — | 1068 |
Frequently asked questions
Is Gemma 2 2b IT better than Gemma 3 4B?
Gemma 2 2b IT is the stronger model overall, scoring 33.1 to 28.1 on the Noometry Index.
Is Gemma 2 2b IT or Gemma 3 4B better for coding?
Gemma 3 4B scores higher on coding benchmarks: 35.9 versus 32.3 in the Noometry coding category.
How many benchmarks do Gemma 2 2b IT and Gemma 3 4B share?
12 benchmarks have published results for both models. Gemma 2 2b IT has 17 scored results on Noometry and Gemma 3 4B has 22.