# Gemma 2 9B vs o1

> o1 is the stronger model overall, scoring 40.9 to 25.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2-9b-vs-o1
- Last updated: 2026-10-11
- Shared benchmarks: 28

## Summary

- They share 28 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and o1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o1 leads 41.5 to 9.7.
- The biggest single-benchmark swing is LiveBench Reasoning: 15.2% for Gemma 2 9B and 91.6% for o1.
- Gemma 2 9B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 2 9B | o1 |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 25.9 | 40.9 |
| Rank | 341 | 143 |
| Context | — | 200K |
| Input $/M | — | $15 |
| Output $/M | — | $60 |
| Weights | Open | Proprietary |

## Coding

- Gemma 2 9B: 29.4 (#304)
- o1: 46.1 (#70)

| Benchmark | Gemma 2 9B | o1 |
|---|---|---|
| LiveBench Coding | 22.5% | 69.7% |
| LMArena Coding | 1173 | 1367 |
| Aider Polyglot | — | 61.7% |
| WeirdML | — | 47.6% |
| BigCodeBench Instruct | 34.7% | — |
| BigCodeBench Complete | 40.6% | — |
| CadEval | — | 56% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |

## Agentic & Tool Use

- Gemma 2 9B: —
- o1: 24.6 (#117)

| Benchmark | Gemma 2 9B | o1 |
|---|---|---|
| Cybench | — | 10% |
| METR Time Horizons | — | 51.1% |

## Reasoning

- Gemma 2 9B: 15.9 (#309)
- o1: 27.9 (#111)

| Benchmark | Gemma 2 9B | o1 |
|---|---|---|
| LiveBench Reasoning | 15.2% | 91.6% |
| LMArena Hard Prompts | 1171 | 1371 |
| LiveBench Data Analysis | 36.4% | 65.5% |
| Epoch Capabilities Index | 119.83 | 141.91 |
| LiveBench | 28.7% | 75.7% |
| SimpleBench | — | 41.7% |
| ARC-AGI-1 | — | 30.7% |
| Chess Puzzles | — | 15% |
| EnigmaEval | — | 5.7% |
| DTBench | — | 74.7% |
| LMCA | — | 22.3% |
| PIQA | 83.7% | — |

## Math

- Gemma 2 9B: 9.9 (#318)
- o1: 36.1 (#175)

| Benchmark | Gemma 2 9B | o1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 73.3% |
| LiveBench Math | 19.8% | 80.3% |
| LMArena Math | 1183 | 1388 |
| MATH Level 5 | 21% | 94.7% |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| FrontierMath (Feb 2025 set) | — | 9.3% |
| GSM8K | 84.9% | — |

## Knowledge

- Gemma 2 9B: 9.7 (#305)
- o1: 41.5 (#110)

| Benchmark | Gemma 2 9B | o1 |
|---|---|---|
| GPQA Diamond | 27.5% | 76.8% |
| LMArena Expert | 1147 | 1361 |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| Confabulations | — | 11.7% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |

## Multimodal

- Gemma 2 9B: —
- o1: 34.2 (#93)

| Benchmark | Gemma 2 9B | o1 |
|---|---|---|
| LMArena Vision | — | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |

## Multilingual

- Gemma 2 9B: 36.6 (#238)
- o1: 48.6 (#142)

| Benchmark | Gemma 2 9B | o1 |
|---|---|---|
| LMArena Non-English | 1188 | 1358 |
| LMArena Chinese | 1185 | 1394 |
| LMArena French | 1190 | 1344 |
| LMArena German | 1186 | 1337 |
| LMArena Japanese | 1144 | 1346 |
| LMArena Korean | 1137 | 1396 |
| LMArena Russian | 1200 | 1356 |
| LMArena Spanish | 1200 | 1345 |

## Instruction Following

- Gemma 2 9B: 57.6 (#269)
- o1: 74.8 (#86)

| Benchmark | Gemma 2 9B | o1 |
|---|---|---|
| LiveBench Instruction Following | 52.6% | 81.5% |
| LMArena Instruction Following | 1178 | 1367 |

## Long Context

- Gemma 2 9B: 36.3 (#233)
- o1: 50.3 (#9)

| Benchmark | Gemma 2 9B | o1 |
|---|---|---|
| LMArena Longer Query | 1197 | 1378 |
| Fiction.LiveBench | — | 83.3% |

## Writing & Preference

- Gemma 2 9B: 32.1 (#281)
- o1: 55.6 (#144)

| Benchmark | Gemma 2 9B | o1 |
|---|---|---|
| LMArena Text | 1207 | 1366 |
| LMArena Creative Writing | 1206 | 1348 |
| LMArena Multi-Turn | 1193 | 1369 |
| LiveBench Language | 25.5% | 65.4% |
| Short-Story Creative Writing | — | 70.2% |
| EQ-Bench Creative Writing | 841 | — |

## FAQ

### Is Gemma 2 9B better than o1?

o1 is the stronger model overall, scoring 40.9 to 25.9 on the Noometry Index.

### Is Gemma 2 9B or o1 better for coding?

o1 scores higher on coding benchmarks: 46.1 versus 29.4 in the Noometry coding category.

### How many benchmarks do Gemma 2 9B and o1 share?

28 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and o1 has 52.