Model comparison
Gemma 1.1 2b IT vs Gemma 3 4B
Gemma 1.1 2b IT and Gemma 3 4B score almost the same on the Noometry Index (28.8 vs 27.9), so choose on price, context window or the category you care about most.
Last verified . 12 shared benchmarks.
GoogleSummary
- They share 12 benchmarks with published results for both. Gemma 1.1 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 multilingual, where Gemma 3 4B leads 42.7 to 24.7.
Side by side
| Gemma 1.1 2b IT | Gemma 3 4B | |
|---|---|---|
| Provider | ||
| Noometry Index | 28.8 | 27.9 |
| 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 | 16 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 4B leads
Gemma 1.1 2b IT: 29.6 (#294), Gemma 3 4B: 35.3 (#214)
| Benchmark | Gemma 1.1 2b IT | Gemma 3 4B |
|---|---|---|
| LMArena Coding | 1034 | 1230 |
| HumanEval+ | 17.7% | — |
| MBPP+ | 23.3% | — |
Agentic & Tool Use Not comparable
Gemma 1.1 2b IT: —, Gemma 3 4B: 20.7 (#134)
| Benchmark | Gemma 1.1 2b IT | Gemma 3 4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 19.6% |
Reasoning Gemma 1.1 2b IT leads
Gemma 1.1 2b IT: 18.2 (#268), Gemma 3 4B: 12.7 (#330)
| Benchmark | Gemma 1.1 2b IT | Gemma 3 4B |
|---|---|---|
| LMArena Hard Prompts | 1005 | 1253 |
| Kagi LLM Benchmark | — | 25.2% |
| Chess Puzzles | — | 0% |
| DTBench | — | 50.9% |
| LMCA | — | 2.8% |
| Epoch Capabilities Index | — | 116.02 |
Math Gemma 1.1 2b IT leads
Gemma 1.1 2b IT: 28.3 (#230), Gemma 3 4B: 15.8 (#286)
| Benchmark | Gemma 1.1 2b IT | Gemma 3 4B |
|---|---|---|
| LMArena Math | 1047 | 1239 |
| OTIS Mock AIME 2024-2025 | — | 7.5% |
Knowledge Gemma 1.1 2b IT leads
Gemma 1.1 2b IT: 26.0 (#255), Gemma 3 4B: 11.8 (#294)
| Benchmark | Gemma 1.1 2b IT | Gemma 3 4B |
|---|---|---|
| LMArena Expert | 970 | 1223 |
| GPQA Diamond | — | 23.2% |
| Vectara Hallucination Rate | — | 6.4% |
Multilingual Gemma 3 4B leads
Gemma 1.1 2b IT: 24.7 (#284), Gemma 3 4B: 42.7 (#189)
| Benchmark | Gemma 1.1 2b IT | Gemma 3 4B |
|---|---|---|
| LMArena Non-English | 988 | 1273 |
| LMArena German | 944 | 1281 |
| LMArena Russian | 990 | 1294 |
| LMArena Chinese | 1011 | — |
| LMArena Korean | 899 | — |
Instruction Following Gemma 3 4B leads
Gemma 1.1 2b IT: 50.1 (#294), Gemma 3 4B: 65.4 (#219)
| Benchmark | Gemma 1.1 2b IT | Gemma 3 4B |
|---|---|---|
| LMArena Instruction Following | 992 | 1239 |
Long Context Gemma 3 4B leads
Gemma 1.1 2b IT: 30.5 (#281), Gemma 3 4B: 38.6 (#189)
| Benchmark | Gemma 1.1 2b IT | Gemma 3 4B |
|---|---|---|
| LMArena Longer Query | 1003 | 1274 |
Writing & Preference Gemma 3 4B leads
Gemma 1.1 2b IT: 25.3 (#301), Gemma 3 4B: 42.2 (#234)
| Benchmark | Gemma 1.1 2b IT | Gemma 3 4B |
|---|---|---|
| LMArena Text | 1022 | 1291 |
| LMArena Creative Writing | 998 | 1270 |
| LMArena Multi-Turn | 958 | 1255 |
| EQ-Bench Creative Writing | — | 1068 |
Frequently asked questions
Is Gemma 1.1 2b IT better than Gemma 3 4B?
Gemma 1.1 2b IT and Gemma 3 4B score almost the same on the Noometry Index (28.8 vs 27.9), so choose on price, context window or the category you care about most.
Is Gemma 1.1 2b IT or Gemma 3 4B better for coding?
Gemma 3 4B scores higher on coding benchmarks: 35.3 versus 29.6 in the Noometry coding category.
How many benchmarks do Gemma 1.1 2b IT and Gemma 3 4B share?
12 benchmarks have published results for both models. Gemma 1.1 2b IT has 16 scored results on Noometry and Gemma 3 4B has 22.