Model comparison
Gemma 3 27B vs Olmo 2 0325 32b Instruct
Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.7 to 30.8 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 3 27B scores higher in 4 categories and Olmo 2 0325 32b Instruct in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Olmo 2 0325 32b Instruct leads 35.2 to 22.5.
Side by side
| Gemma 3 27B | Olmo 2 0325 32b Instruct | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | |
| Noometry Index | 30.8 | 32.7 |
| Released | 2025-03-11 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.08 | — |
| Output $ / M tokens | $0.16 | — |
| Results tracked | 43 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 2 0325 32b Instruct leads
Gemma 3 27B: 22.5 (#334), Olmo 2 0325 32b Instruct: 35.2 (#227)
| Benchmark | Gemma 3 27B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Coding | 1322 | 1210 |
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| LiveBench Coding | 39.9% | — |
Agentic & Tool Use Not comparable
Gemma 3 27B: 25.1 (#110), Olmo 2 0325 32b Instruct: —
| Benchmark | Gemma 3 27B | Olmo 2 0325 32b Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning Olmo 2 0325 32b Instruct leads
Gemma 3 27B: 16.7 (#301), Olmo 2 0325 32b Instruct: 23.6 (#175)
| Benchmark | Gemma 3 27B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1340 | 1208 |
| Kagi LLM Benchmark | 40.4% | — |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| Epoch Capabilities Index | 130.04 | — |
| LiveBench | 50% | — |
Math Too close to call
Gemma 3 27B: 25.9 (#265), Olmo 2 0325 32b Instruct: 26.8 (#255)
| Benchmark | Gemma 3 27B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Math | 1312 | 1208 |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| Omni-MATH | — | 16.1% |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge Gemma 3 27B leads
Gemma 3 27B: 25.5 (#261), Olmo 2 0325 32b Instruct: 19.5 (#279)
| Benchmark | Gemma 3 27B | Olmo 2 0325 32b Instruct |
|---|---|---|
| GPQA Diamond | 47.7% | — |
| MMLU-Pro | — | 41.4% |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
| GPQA (HELM) | — | 28.7% |
| LMArena Expert | 1304 | — |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), Olmo 2 0325 32b Instruct: —
| Benchmark | Gemma 3 27B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual Gemma 3 27B leads
Gemma 3 27B: 46.9 (#155), Olmo 2 0325 32b Instruct: 34.8 (#248)
| Benchmark | Gemma 3 27B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Non-English | 1334 | 1160 |
| LMArena Chinese | 1346 | 1192 |
| LMArena Russian | 1349 | 1187 |
| LMArena French | 1368 | — |
| LMArena German | 1362 | — |
| LMArena Japanese | 1287 | — |
| LMArena Korean | 1308 | — |
| LMArena Spanish | 1349 | — |
Instruction Following Gemma 3 27B leads
Gemma 3 27B: 70.6 (#160), Olmo 2 0325 32b Instruct: 61.5 (#244)
| Benchmark | Gemma 3 27B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Instruction Following | 1321 | 1186 |
| LiveBench Instruction Following | 74.9% | — |
| IFEval | — | 78% |
Long Context Olmo 2 0325 32b Instruct leads
Gemma 3 27B: 27.6 (#293), Olmo 2 0325 32b Instruct: 36.2 (#234)
| Benchmark | Gemma 3 27B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1333 | 1194 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Gemma 3 27B leads
Gemma 3 27B: 52.5 (#168), Olmo 2 0325 32b Instruct: 42.1 (#236)
| Benchmark | Gemma 3 27B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Text | 1358 | 1218 |
| LMArena Creative Writing | 1346 | 1199 |
| LMArena Multi-Turn | 1345 | 1221 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| WildBench | — | 73.4% |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Olmo 2 0325 32b Instruct?
Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.7 to 30.8 on the Noometry Index.
Is Gemma 3 27B or Olmo 2 0325 32b Instruct better for coding?
Olmo 2 0325 32b Instruct scores higher on coding benchmarks: 35.2 versus 22.5 in the Noometry coding category.
How many benchmarks do Gemma 3 27B and Olmo 2 0325 32b Instruct share?
11 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Olmo 2 0325 32b Instruct has 16.