Model comparison
Gemma 3 4B vs Olmo 2 0325 32b Instruct
Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.7 to 28.1 on the Noometry Index.
Last verified . 10 shared benchmarks.
Google
Allen Institute for AI (Ai2)Summary
- They share 10 benchmarks with published results for both. Gemma 3 4B scores higher in 4 categories and Olmo 2 0325 32b Instruct in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Olmo 2 0325 32b Instruct leads 23.6 to 13.2.
Side by side
| Gemma 3 4B | Olmo 2 0325 32b Instruct | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | |
| Noometry Index | 28.1 | 32.7 |
| 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 | 22 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 3 4B: 35.9 (#215), Olmo 2 0325 32b Instruct: 35.2 (#227)
| Benchmark | Gemma 3 4B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Coding | 1230 | 1210 |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), Olmo 2 0325 32b Instruct: —
| Benchmark | Gemma 3 4B | Olmo 2 0325 32b Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Olmo 2 0325 32b Instruct leads
Gemma 3 4B: 13.2 (#335), Olmo 2 0325 32b Instruct: 23.6 (#175)
| Benchmark | Gemma 3 4B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1253 | 1208 |
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |
Math Olmo 2 0325 32b Instruct leads
Gemma 3 4B: 16.8 (#292), Olmo 2 0325 32b Instruct: 26.8 (#255)
| Benchmark | Gemma 3 4B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Math | 1239 | 1208 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |
| Omni-MATH | — | 16.1% |
Knowledge Olmo 2 0325 32b Instruct leads
Gemma 3 4B: 11.8 (#299), Olmo 2 0325 32b Instruct: 19.5 (#279)
| Benchmark | Gemma 3 4B | Olmo 2 0325 32b Instruct |
|---|---|---|
| GPQA Diamond | 23.2% | — |
| MMLU-Pro | — | 41.4% |
| Vectara Hallucination Rate | 6.4% | — |
| GPQA (HELM) | — | 28.7% |
| LMArena Expert | 1223 | — |
Multilingual Gemma 3 4B leads
Gemma 3 4B: 42.5 (#194), Olmo 2 0325 32b Instruct: 34.8 (#248)
| Benchmark | Gemma 3 4B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Non-English | 1273 | 1160 |
| LMArena Russian | 1294 | 1187 |
| LMArena Chinese | — | 1192 |
| LMArena German | 1281 | — |
Instruction Following Gemma 3 4B leads
Gemma 3 4B: 65.2 (#225), Olmo 2 0325 32b Instruct: 61.5 (#244)
| Benchmark | Gemma 3 4B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Instruction Following | 1239 | 1186 |
| IFEval | — | 78% |
Long Context Gemma 3 4B leads
Gemma 3 4B: 38.7 (#194), Olmo 2 0325 32b Instruct: 36.2 (#234)
| Benchmark | Gemma 3 4B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1273 | 1194 |
Writing & Preference Too close to call
Gemma 3 4B: 42.0 (#239), Olmo 2 0325 32b Instruct: 42.1 (#236)
| Benchmark | Gemma 3 4B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Text | 1291 | 1218 |
| LMArena Creative Writing | 1271 | 1199 |
| LMArena Multi-Turn | 1255 | 1221 |
| EQ-Bench Creative Writing | 1068 | — |
| WildBench | — | 73.4% |
Frequently asked questions
Is Gemma 3 4B better than Olmo 2 0325 32b Instruct?
Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.7 to 28.1 on the Noometry Index.
Is Gemma 3 4B or Olmo 2 0325 32b Instruct better for coding?
They score almost the same on coding (35.9 vs 35.2); test both on your own repository before choosing.
How many benchmarks do Gemma 3 4B and Olmo 2 0325 32b Instruct share?
10 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Olmo 2 0325 32b Instruct has 16.