Model comparison
Gemma 3 12B vs Olmo 3.1 32b Instruct
Olmo 3.1 32b Instruct is the stronger model overall, scoring 39.4 to 32.1 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 12B scores higher in 3 categories and Olmo 3.1 32b Instruct in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Olmo 3.1 32b Instruct leads 36.3 to 22.3.
Side by side
| Gemma 3 12B | Olmo 3.1 32b Instruct | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | |
| Noometry Index | 32.1 | 39.4 |
| Released | 2025-03-12 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 24 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 3.1 32b Instruct leads
Gemma 3 12B: 31.7 (#280), Olmo 3.1 32b Instruct: 39.5 (#157)
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Coding | 1281 | 1347 |
| SciCode | 17.4% | — |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.5 (#108), Olmo 3.1 32b Instruct: —
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning Olmo 3.1 32b Instruct leads
Gemma 3 12B: 15.7 (#313), Olmo 3.1 32b Instruct: 26.4 (#132)
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1322 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.5 | — |
Math Olmo 3.1 32b Instruct leads
Gemma 3 12B: 22.3 (#279), Olmo 3.1 32b Instruct: 36.3 (#167)
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Math | 1307 | 1305 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
Knowledge Olmo 3.1 32b Instruct leads
Gemma 3 12B: 26.5 (#257), Olmo 3.1 32b Instruct: 36.1 (#175)
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Expert | 1248 | 1308 |
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
Multimodal Not comparable
Gemma 3 12B: —, Olmo 3.1 32b Instruct: —
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Instruct |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Gemma 3 12B leads
Gemma 3 12B: 45.7 (#165), Olmo 3.1 32b Instruct: 42.6 (#191)
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Non-English | 1318 | 1275 |
| LMArena German | 1370 | 1282 |
| LMArena Russian | 1335 | 1268 |
| LMArena Chinese | — | 1304 |
| LMArena French | — | 1328 |
| LMArena Korean | — | 1206 |
| LMArena Spanish | — | 1336 |
Instruction Following Too close to call
Gemma 3 12B: 68.6 (#186), Olmo 3.1 32b Instruct: 68.6 (#187)
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Instruction Following | 1299 | 1299 |
Long Context Too close to call
Gemma 3 12B: 40.0 (#162), Olmo 3.1 32b Instruct: 39.9 (#166)
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1317 | 1312 |
Writing & Preference Olmo 3.1 32b Instruct leads
Gemma 3 12B: 47.5 (#209), Olmo 3.1 32b Instruct: 50.2 (#185)
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Text | 1334 | 1311 |
| LMArena Creative Writing | 1331 | 1264 |
| LMArena Multi-Turn | 1334 | 1309 |
| EQ-Bench Creative Writing | 1126 | — |
Frequently asked questions
Is Gemma 3 12B better than Olmo 3.1 32b Instruct?
Olmo 3.1 32b Instruct is the stronger model overall, scoring 39.4 to 32.1 on the Noometry Index.
Is Gemma 3 12B or Olmo 3.1 32b Instruct better for coding?
Olmo 3.1 32b Instruct scores higher on coding benchmarks: 39.5 versus 31.7 in the Noometry coding category.
How many benchmarks do Gemma 3 12B and Olmo 3.1 32b Instruct share?
12 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Olmo 3.1 32b Instruct has 16.