Model comparison
Gemma 2B vs Olmo 2 0325 32b Instruct
Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.7 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 1 category and Olmo 2 0325 32b Instruct in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Olmo 2 0325 32b Instruct leads 42.1 to 24.0.
Side by side
| Gemma 2B | Olmo 2 0325 32b Instruct | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | |
| Noometry Index | 29.6 | 32.7 |
| Released | 2024-02-21 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 23 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 2 0325 32b Instruct leads
Gemma 2B: 29.4 (#305), Olmo 2 0325 32b Instruct: 35.2 (#227)
| Benchmark | Gemma 2B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Coding | 1010 | 1210 |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Reasoning Olmo 2 0325 32b Instruct leads
Gemma 2B: 18.8 (#275), Olmo 2 0325 32b Instruct: 23.6 (#175)
| Benchmark | Gemma 2B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 989 | 1208 |
| BIG-Bench Hard | 35.2% | — |
| Epoch Capabilities Index | 94.2 | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Gemma 2B leads
Gemma 2B: 30.0 (#239), Olmo 2 0325 32b Instruct: 26.8 (#255)
| Benchmark | Gemma 2B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Math | 1009 | 1208 |
| Omni-MATH | — | 16.1% |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Olmo 2 0325 32b Instruct: 19.5 (#279)
| Benchmark | Gemma 2B | Olmo 2 0325 32b Instruct |
|---|---|---|
| MMLU-Pro | — | 41.4% |
| GPQA (HELM) | — | 28.7% |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual Olmo 2 0325 32b Instruct leads
Gemma 2B: 23.0 (#294), Olmo 2 0325 32b Instruct: 34.8 (#248)
| Benchmark | Gemma 2B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Non-English | 958 | 1160 |
| LMArena Chinese | 986 | 1192 |
| LMArena Russian | 937 | 1187 |
Instruction Following Olmo 2 0325 32b Instruct leads
Gemma 2B: 48.5 (#302), Olmo 2 0325 32b Instruct: 61.5 (#244)
| Benchmark | Gemma 2B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Instruction Following | 970 | 1186 |
| IFEval | — | 78% |
Long Context Olmo 2 0325 32b Instruct leads
Gemma 2B: 29.9 (#291), Olmo 2 0325 32b Instruct: 36.2 (#234)
| Benchmark | Gemma 2B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Longer Query | 981 | 1194 |
Writing & Preference Olmo 2 0325 32b Instruct leads
Gemma 2B: 24.0 (#308), Olmo 2 0325 32b Instruct: 42.1 (#236)
| Benchmark | Gemma 2B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Text | 1002 | 1218 |
| LMArena Creative Writing | 987 | 1199 |
| LMArena Multi-Turn | 945 | 1221 |
| WildBench | — | 73.4% |
Frequently asked questions
Is Gemma 2B better than Olmo 2 0325 32b Instruct?
Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.7 to 29.6 on the Noometry Index.
Is Gemma 2B or Olmo 2 0325 32b Instruct better for coding?
Olmo 2 0325 32b Instruct scores higher on coding benchmarks: 35.2 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2B and Olmo 2 0325 32b Instruct share?
11 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Olmo 2 0325 32b Instruct has 16.