Model comparison
Gemma 7B vs Olmo 2 0325 32b Instruct
Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.2 to 29.5 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 7B scores higher in 2 categories and Olmo 2 0325 32b Instruct in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Olmo 2 0325 32b Instruct leads 42.3 to 27.2.
Side by side
| Gemma 7B | Olmo 2 0325 32b Instruct | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | |
| Noometry Index | 29.5 | 32.2 |
| Released | 2024-02-21 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 27 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 2 0325 32b Instruct leads
Gemma 7B: 29.9 (#290), Olmo 2 0325 32b Instruct: 34.6 (#222)
| Benchmark | Gemma 7B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Coding | 1048 | 1210 |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |
Reasoning Olmo 2 0325 32b Instruct leads
Gemma 7B: 19.0 (#247), Olmo 2 0325 32b Instruct: 22.6 (#174)
| Benchmark | Gemma 7B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1208 |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| Epoch Capabilities Index | 111.74 | — |
| HellaSwag | 82.2% | — |
| PIQA | 81.2% | — |
| WinoGrande | 79% | — |
Math Gemma 7B leads
Gemma 7B: 28.7 (#225), Olmo 2 0325 32b Instruct: 24.8 (#255)
| Benchmark | Gemma 7B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Math | 1066 | 1208 |
| Omni-MATH | — | 16.1% |
| GSM8K | 46.4% | — |
Knowledge Gemma 7B leads
Gemma 7B: 26.8 (#248), Olmo 2 0325 32b Instruct: 19.2 (#274)
| Benchmark | Gemma 7B | Olmo 2 0325 32b Instruct |
|---|---|---|
| MMLU-Pro | — | 41.4% |
| GPQA (HELM) | — | 28.7% |
| LMArena Expert | 1002 | — |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| MMLU | 66.1% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |
Multilingual Olmo 2 0325 32b Instruct leads
Gemma 7B: 25.3 (#282), Olmo 2 0325 32b Instruct: 35.0 (#243)
| Benchmark | Gemma 7B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Non-English | 999 | 1160 |
| LMArena Chinese | 1035 | 1192 |
| LMArena Russian | 993 | 1187 |
| LMArena French | 1024 | — |
Instruction Following Olmo 2 0325 32b Instruct leads
Gemma 7B: 51.7 (#290), Olmo 2 0325 32b Instruct: 61.8 (#238)
| Benchmark | Gemma 7B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Instruction Following | 1017 | 1186 |
| IFEval | — | 78% |
Long Context Olmo 2 0325 32b Instruct leads
Gemma 7B: 31.1 (#277), Olmo 2 0325 32b Instruct: 36.2 (#229)
| Benchmark | Gemma 7B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1022 | 1194 |
Writing & Preference Olmo 2 0325 32b Instruct leads
Gemma 7B: 27.2 (#297), Olmo 2 0325 32b Instruct: 42.3 (#231)
| Benchmark | Gemma 7B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Text | 1056 | 1218 |
| LMArena Creative Writing | 1024 | 1199 |
| LMArena Multi-Turn | 963 | 1221 |
| WildBench | — | 73.4% |
Frequently asked questions
Is Gemma 7B better than Olmo 2 0325 32b Instruct?
Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.2 to 29.5 on the Noometry Index.
Is Gemma 7B or Olmo 2 0325 32b Instruct better for coding?
Olmo 2 0325 32b Instruct scores higher on coding benchmarks: 34.6 versus 29.9 in the Noometry coding category.
How many benchmarks do Gemma 7B and Olmo 2 0325 32b Instruct share?
11 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Olmo 2 0325 32b Instruct has 16.