Model comparison
Gemma 3 4B vs Palm 2
Palm 2 is the stronger model overall, scoring 29.4 to 27.9 on the Noometry Index.
Last verified . 9 shared benchmarks.
GoogleSummary
- They share 9 benchmarks with published results for both. Gemma 3 4B scores higher in 5 categories and Palm 2 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemma 3 4B leads 42.7 to 21.1.
- Gemma 3 4B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 4B | Palm 2 | |
|---|---|---|
| Provider | ||
| Noometry Index | 27.9 | 29.4 |
| Released | 2025-03-12 | — |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 22 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 4B leads
Gemma 3 4B: 35.3 (#214), Palm 2: 28.5 (#306)
| Benchmark | Gemma 3 4B | Palm 2 |
|---|---|---|
| LMArena Coding | 1230 | 995 |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.7 (#134), Palm 2: —
| Benchmark | Gemma 3 4B | Palm 2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Palm 2 leads
Gemma 3 4B: 12.7 (#330), Palm 2: 18.2 (#270)
| Benchmark | Gemma 3 4B | Palm 2 |
|---|---|---|
| LMArena Hard Prompts | 1253 | 1005 |
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |
Math Palm 2 leads
Gemma 3 4B: 15.8 (#286), Palm 2: 28.4 (#229)
| Benchmark | Gemma 3 4B | Palm 2 |
|---|---|---|
| LMArena Math | 1239 | 1049 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |
Knowledge Not comparable
Gemma 3 4B: 11.8 (#294), Palm 2: —
| Benchmark | Gemma 3 4B | Palm 2 |
|---|---|---|
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |
| LMArena Expert | 1223 | — |
Multilingual Gemma 3 4B leads
Gemma 3 4B: 42.7 (#189), Palm 2: 21.1 (#290)
| Benchmark | Gemma 3 4B | Palm 2 |
|---|---|---|
| LMArena Non-English | 1273 | 916 |
| LMArena Chinese | — | 887 |
| LMArena German | 1281 | — |
| LMArena Russian | 1294 | — |
Instruction Following Gemma 3 4B leads
Gemma 3 4B: 65.4 (#219), Palm 2: 51.3 (#291)
| Benchmark | Gemma 3 4B | Palm 2 |
|---|---|---|
| LMArena Instruction Following | 1239 | 1010 |
Long Context Gemma 3 4B leads
Gemma 3 4B: 38.6 (#189), Palm 2: 30.7 (#280)
| Benchmark | Gemma 3 4B | Palm 2 |
|---|---|---|
| LMArena Longer Query | 1274 | 1010 |
Writing & Preference Gemma 3 4B leads
Gemma 3 4B: 42.2 (#234), Palm 2: 25.7 (#299)
| Benchmark | Gemma 3 4B | Palm 2 |
|---|---|---|
| LMArena Text | 1291 | 1027 |
| LMArena Creative Writing | 1270 | 991 |
| LMArena Multi-Turn | 1255 | 994 |
| EQ-Bench Creative Writing | 1068 | — |
Frequently asked questions
Is Gemma 3 4B better than Palm 2?
Palm 2 is the stronger model overall, scoring 29.4 to 27.9 on the Noometry Index.
Is Gemma 3 4B or Palm 2 better for coding?
Gemma 3 4B scores higher on coding benchmarks: 35.3 versus 28.5 in the Noometry coding category.
How many benchmarks do Gemma 3 4B and Palm 2 share?
9 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Palm 2 has 10.