Model comparison
Gemma 3 4B vs Olmo 3.1 32b Think
Olmo 3.1 32b Think is the stronger model overall, scoring 37.9 to 28.1 on the Noometry Index.
Last verified . 12 shared benchmarks.
Google
Allen Institute for AI (Ai2)Summary
- They share 12 benchmarks with published results for both. Gemma 3 4B scores higher in 2 categories and Olmo 3.1 32b Think in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Olmo 3.1 32b Think leads 35.7 to 11.8.
Side by side
| Gemma 3 4B | Olmo 3.1 32b Think | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | |
| Noometry Index | 28.1 | 37.9 |
| 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 | 22 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 3.1 32b Think leads
Gemma 3 4B: 35.9 (#215), Olmo 3.1 32b Think: 37.7 (#189)
| Benchmark | Gemma 3 4B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Coding | 1230 | 1291 |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), Olmo 3.1 32b Think: —
| Benchmark | Gemma 3 4B | Olmo 3.1 32b Think |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Olmo 3.1 32b Think leads
Gemma 3 4B: 13.2 (#335), Olmo 3.1 32b Think: 25.2 (#150)
| Benchmark | Gemma 3 4B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1253 | 1272 |
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |
Math Olmo 3.1 32b Think leads
Gemma 3 4B: 16.8 (#292), Olmo 3.1 32b Think: 36.3 (#168)
| Benchmark | Gemma 3 4B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Math | 1239 | 1305 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |
Knowledge Olmo 3.1 32b Think leads
Gemma 3 4B: 11.8 (#299), Olmo 3.1 32b Think: 35.7 (#181)
| Benchmark | Gemma 3 4B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Expert | 1223 | 1295 |
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |
Multilingual Gemma 3 4B leads
Gemma 3 4B: 42.5 (#194), Olmo 3.1 32b Think: 38.1 (#231)
| Benchmark | Gemma 3 4B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Non-English | 1273 | 1209 |
| LMArena German | 1281 | 1262 |
| LMArena Russian | 1294 | 1193 |
| LMArena Chinese | — | 1242 |
| LMArena French | — | 1260 |
| LMArena Spanish | — | 1289 |
Instruction Following Too close to call
Gemma 3 4B: 65.2 (#225), Olmo 3.1 32b Think: 65.6 (#218)
| Benchmark | Gemma 3 4B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Instruction Following | 1239 | 1247 |
Long Context Too close to call
Gemma 3 4B: 38.7 (#194), Olmo 3.1 32b Think: 38.6 (#195)
| Benchmark | Gemma 3 4B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Longer Query | 1273 | 1272 |
Writing & Preference Olmo 3.1 32b Think leads
Gemma 3 4B: 42.0 (#239), Olmo 3.1 32b Think: 46.2 (#220)
| Benchmark | Gemma 3 4B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Text | 1291 | 1272 |
| LMArena Creative Writing | 1271 | 1226 |
| LMArena Multi-Turn | 1255 | 1252 |
| EQ-Bench Creative Writing | 1068 | — |
Frequently asked questions
Is Gemma 3 4B better than Olmo 3.1 32b Think?
Olmo 3.1 32b Think is the stronger model overall, scoring 37.9 to 28.1 on the Noometry Index.
Is Gemma 3 4B or Olmo 3.1 32b Think better for coding?
Olmo 3.1 32b Think scores higher on coding benchmarks: 37.7 versus 35.9 in the Noometry coding category.
How many benchmarks do Gemma 3 4B and Olmo 3.1 32b Think share?
12 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Olmo 3.1 32b Think has 15.