Model comparison
Gemma 2B vs Olmo 3 32b Think
Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 29.6 on the Noometry Index.
Last verified . 11 shared benchmarks.
Google
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and Olmo 3 32b Think in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Olmo 3 32b Think leads 49.1 to 24.0.
Side by side
| Gemma 2B | Olmo 3 32b Think | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | |
| Noometry Index | 29.6 | 38.7 |
| Released | 2024-02-21 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 23 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 3 32b Think leads
Gemma 2B: 29.4 (#305), Olmo 3 32b Think: 38.6 (#172)
| Benchmark | Gemma 2B | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | 1010 | 1319 |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Reasoning Olmo 3 32b Think leads
Gemma 2B: 18.8 (#275), Olmo 3 32b Think: 25.9 (#140)
| Benchmark | Gemma 2B | Olmo 3 32b Think |
|---|---|---|
| LMArena Hard Prompts | 989 | 1302 |
| BIG-Bench Hard | 35.2% | — |
| Epoch Capabilities Index | 94.2 | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Olmo 3 32b Think leads
Gemma 2B: 30.0 (#239), Olmo 3 32b Think: 36.5 (#165)
| Benchmark | Gemma 2B | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | 1009 | 1316 |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Olmo 3 32b Think: 35.0 (#190)
| Benchmark | Gemma 2B | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | — | 1273 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual Olmo 3 32b Think leads
Gemma 2B: 23.0 (#294), Olmo 3 32b Think: 41.2 (#210)
| Benchmark | Gemma 2B | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | 958 | 1255 |
| LMArena Chinese | 986 | 1300 |
| LMArena Russian | 937 | 1254 |
| LMArena French | — | 1291 |
| LMArena German | — | 1290 |
Instruction Following Olmo 3 32b Think leads
Gemma 2B: 48.5 (#302), Olmo 3 32b Think: 67.2 (#198)
| Benchmark | Gemma 2B | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | 970 | 1275 |
Long Context Olmo 3 32b Think leads
Gemma 2B: 29.9 (#291), Olmo 3 32b Think: 39.4 (#182)
| Benchmark | Gemma 2B | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | 981 | 1296 |
Writing & Preference Olmo 3 32b Think leads
Gemma 2B: 24.0 (#308), Olmo 3 32b Think: 49.1 (#193)
| Benchmark | Gemma 2B | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | 1002 | 1300 |
| LMArena Creative Writing | 987 | 1256 |
| LMArena Multi-Turn | 945 | 1290 |
Frequently asked questions
Is Gemma 2B better than Olmo 3 32b Think?
Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 29.6 on the Noometry Index.
Is Gemma 2B or Olmo 3 32b Think better for coding?
Olmo 3 32b Think scores higher on coding benchmarks: 38.6 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2B and Olmo 3 32b Think share?
11 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Olmo 3 32b Think has 14.