Model comparison
Gemma 3 12B vs Olmo 3.1 32b Think
Olmo 3.1 32b Think is the stronger model overall, scoring 37.3 to 31.8 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 4 categories and Olmo 3.1 32b Think in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Olmo 3.1 32b Think leads 33.6 to 21.0.
Side by side
| Gemma 3 12B | Olmo 3.1 32b Think | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | |
| Noometry Index | 31.8 | 37.3 |
| 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 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 3.1 32b Think leads
Gemma 3 12B: 31.2 (#276), Olmo 3.1 32b Think: 37.1 (#186)
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Coding | 1281 | 1292 |
| SciCode | 17.4% | — |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.3 (#101), Olmo 3.1 32b Think: —
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Think |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning Olmo 3.1 32b Think leads
Gemma 3 12B: 15.2 (#307), Olmo 3.1 32b Think: 24.1 (#151)
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1272 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.49 | — |
Math Olmo 3.1 32b Think leads
Gemma 3 12B: 21.0 (#273), Olmo 3.1 32b Think: 33.6 (#170)
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Math | 1307 | 1305 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
Knowledge Olmo 3.1 32b Think leads
Gemma 3 12B: 26.5 (#250), Olmo 3.1 32b Think: 35.0 (#178)
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Expert | 1248 | 1294 |
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
Multimodal Not comparable
Gemma 3 12B: —, Olmo 3.1 32b Think: —
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Think |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Gemma 3 12B leads
Gemma 3 12B: 45.9 (#160), Olmo 3.1 32b Think: 38.3 (#226)
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Non-English | 1318 | 1210 |
| LMArena German | 1370 | 1260 |
| LMArena Russian | 1335 | 1193 |
| LMArena Chinese | — | 1241 |
| LMArena French | — | 1262 |
| LMArena Spanish | — | 1288 |
Instruction Following Gemma 3 12B leads
Gemma 3 12B: 68.8 (#179), Olmo 3.1 32b Think: 65.8 (#213)
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Instruction Following | 1299 | 1246 |
Long Context Gemma 3 12B leads
Gemma 3 12B: 40.0 (#157), Olmo 3.1 32b Think: 38.6 (#190)
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Longer Query | 1317 | 1272 |
Writing & Preference Gemma 3 12B leads
Gemma 3 12B: 47.7 (#205), Olmo 3.1 32b Think: 46.4 (#215)
| Benchmark | Gemma 3 12B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Text | 1334 | 1271 |
| LMArena Creative Writing | 1331 | 1226 |
| LMArena Multi-Turn | 1334 | 1252 |
| EQ-Bench Creative Writing | 1126 | — |
Frequently asked questions
Is Gemma 3 12B better than Olmo 3.1 32b Think?
Olmo 3.1 32b Think is the stronger model overall, scoring 37.3 to 31.8 on the Noometry Index.
Is Gemma 3 12B or Olmo 3.1 32b Think better for coding?
Olmo 3.1 32b Think scores higher on coding benchmarks: 37.1 versus 31.2 in the Noometry coding category.
How many benchmarks do Gemma 3 12B and Olmo 3.1 32b Think share?
12 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Olmo 3.1 32b Think has 15.