# Gemma 3 12B vs Olmo 3 32b Think

> Olmo 3 32b Think is the stronger model overall, scoring 38.1 to 31.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3-12b-vs-olmo-3-32b-think
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Gemma 3 12B scores higher in 3 categories and Olmo 3 32b Think in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Olmo 3 32b Think leads 33.8 to 21.0.

## Snapshot

| | Gemma 3 12B | Olmo 3 32b Think |
|---|---|---|
| Provider | Google | Allen Institute for AI (Ai2) |
| Noometry Index | 31.8 | 38.1 |
| Rank | 255 | 182 |
| Context | 131K | — |
| Input $/M | $0.05 | — |
| Output $/M | $0.15 | — |
| Weights | Open | Open |

## Coding

- Gemma 3 12B: 31.2 (#276)
- Olmo 3 32b Think: 38.0 (#169)

| Benchmark | Gemma 3 12B | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | 1281 | 1318 |
| SciCode | 17.4% | — |

## Agentic & Tool Use

- Gemma 3 12B: 25.3 (#101)
- Olmo 3 32b Think: —

| Benchmark | Gemma 3 12B | Olmo 3 32b Think |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |

## Reasoning

- Gemma 3 12B: 15.2 (#307)
- Olmo 3 32b Think: 24.9 (#138)

| Benchmark | Gemma 3 12B | Olmo 3 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1302 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.49 | — |

## Math

- Gemma 3 12B: 21.0 (#273)
- Olmo 3 32b Think: 33.8 (#165)

| Benchmark | Gemma 3 12B | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | 1307 | 1315 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |

## Knowledge

- Gemma 3 12B: 26.5 (#250)
- Olmo 3 32b Think: 34.4 (#189)

| Benchmark | Gemma 3 12B | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | 1248 | 1272 |
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |

## Multimodal

- Gemma 3 12B: —
- Olmo 3 32b Think: —

| Benchmark | Gemma 3 12B | Olmo 3 32b Think |
|---|---|---|
| MindCube | 46.7% | — |

## Multilingual

- Gemma 3 12B: 45.9 (#160)
- Olmo 3 32b Think: 41.4 (#205)

| Benchmark | Gemma 3 12B | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | 1318 | 1255 |
| LMArena German | 1370 | 1290 |
| LMArena Russian | 1335 | 1255 |
| LMArena Chinese | — | 1300 |
| LMArena French | — | 1291 |

## Instruction Following

- Gemma 3 12B: 68.8 (#179)
- Olmo 3 32b Think: 67.4 (#193)

| Benchmark | Gemma 3 12B | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | 1299 | 1275 |

## Long Context

- Gemma 3 12B: 40.0 (#157)
- Olmo 3 32b Think: 39.4 (#177)

| Benchmark | Gemma 3 12B | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | 1317 | 1296 |

## Writing & Preference

- Gemma 3 12B: 47.7 (#205)
- Olmo 3 32b Think: 49.2 (#188)

| Benchmark | Gemma 3 12B | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | 1334 | 1300 |
| LMArena Creative Writing | 1331 | 1256 |
| LMArena Multi-Turn | 1334 | 1289 |
| EQ-Bench Creative Writing | 1126 | — |

## FAQ

### Is Gemma 3 12B better than Olmo 3 32b Think?

Olmo 3 32b Think is the stronger model overall, scoring 38.1 to 31.8 on the Noometry Index.

### Is Gemma 3 12B or Olmo 3 32b Think better for coding?

Olmo 3 32b Think scores higher on coding benchmarks: 38.0 versus 31.2 in the Noometry coding category.

### How many benchmarks do Gemma 3 12B and Olmo 3 32b Think share?

12 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Olmo 3 32b Think has 14.