Model comparison
Gemma 2 27B vs o1-mini
o1-mini is the stronger model overall, scoring 34.0 to 29.4 on the Noometry Index.
Last verified . 29 shared benchmarks.
GoogleSummary
- They share 29 benchmarks with published results for both. Gemma 2 27B scores higher in 1 category and o1-mini in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where o1-mini leads 35.4 to 10.7.
- The biggest single-benchmark swing is MATH Level 5: 27.9% for Gemma 2 27B and 89.2% for o1-mini.
- Gemma 2 27B has downloadable open weights; the other is API-only.
Side by side
| Gemma 2 27B | o1-mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 29.4 | 34.0 |
| Released | 2024-06-24 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 8K | — |
| Max output | 2K | — |
| Input $ / M tokens | $0.65 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 34 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1-mini leads
Gemma 2 27B: 34.1 (#246), o1-mini: 35.5 (#224)
| Benchmark | Gemma 2 27B | o1-mini |
|---|---|---|
| LiveBench Coding | 36% | 48% |
| LMArena Coding | 1211 | 1362 |
| Aider Polyglot | — | 32.9% |
| WeirdML | — | 36.3% |
| BigCodeBench Instruct | 42.8% | — |
| BigCodeBench Complete | 52.5% | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use Not comparable
Gemma 2 27B: —, o1-mini: 24.6 (#118)
| Benchmark | Gemma 2 27B | o1-mini |
|---|---|---|
| Cybench | — | 10% |
Reasoning Gemma 2 27B leads
Gemma 2 27B: 15.3 (#315), o1-mini: 8.8 (#346)
| Benchmark | Gemma 2 27B | o1-mini |
|---|---|---|
| LiveBench Reasoning | 28.1% | 72.3% |
| LMArena Hard Prompts | 1198 | 1333 |
| LiveBench Data Analysis | 47.9% | 57.9% |
| Epoch Capabilities Index | 122.08 | 135.82 |
| LiveBench | 38.2% | 57.8% |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 18.1% |
| ARC-AGI-1 | — | 14% |
| DTBench | 48% | — |
| LMCA | 7.1% | — |
Math o1-mini leads
Gemma 2 27B: 10.7 (#311), o1-mini: 35.4 (#186)
| Benchmark | Gemma 2 27B | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.4% | 46.9% |
| LiveBench Math | 26.5% | 62% |
| LMArena Math | 1212 | 1358 |
| MATH Level 5 | 27.9% | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge o1-mini leads
Gemma 2 27B: 19.0 (#280), o1-mini: 34.9 (#192)
| Benchmark | Gemma 2 27B | o1-mini |
|---|---|---|
| GPQA Diamond | 36.5% | 62.4% |
| Confabulations | 27.1% | 18.6% |
| LMArena Expert | 1172 | 1316 |
| MMLU | 75.7% | — |
Multilingual o1-mini leads
Gemma 2 27B: 38.6 (#226), o1-mini: 43.6 (#182)
| Benchmark | Gemma 2 27B | o1-mini |
|---|---|---|
| LMArena Non-English | 1217 | 1289 |
| LMArena Chinese | 1221 | 1314 |
| LMArena French | 1247 | 1293 |
| LMArena German | 1209 | 1278 |
| LMArena Japanese | 1175 | 1245 |
| LMArena Korean | 1174 | 1223 |
| LMArena Russian | 1234 | 1283 |
| LMArena Spanish | 1228 | 1303 |
Instruction Following o1-mini leads
Gemma 2 27B: 60.5 (#249), o1-mini: 66.7 (#206)
| Benchmark | Gemma 2 27B | o1-mini |
|---|---|---|
| LiveBench Instruction Following | 58.1% | 65.4% |
| LMArena Instruction Following | 1206 | 1304 |
Long Context o1-mini leads
Gemma 2 27B: 37.3 (#218), o1-mini: 40.1 (#161)
| Benchmark | Gemma 2 27B | o1-mini |
|---|---|---|
| LMArena Longer Query | 1231 | 1320 |
Writing & Preference o1-mini leads
Gemma 2 27B: 44.2 (#225), o1-mini: 48.4 (#202)
| Benchmark | Gemma 2 27B | o1-mini |
|---|---|---|
| LMArena Text | 1231 | 1317 |
| LMArena Creative Writing | 1241 | 1244 |
| LMArena Multi-Turn | 1224 | 1314 |
| LiveBench Language | 32.6% | 40.9% |
| Short-Story Creative Writing | — | 64.9% |
Frequently asked questions
Is Gemma 2 27B better than o1-mini?
o1-mini is the stronger model overall, scoring 34.0 to 29.4 on the Noometry Index.
Is Gemma 2 27B or o1-mini better for coding?
o1-mini scores higher on coding benchmarks: 35.5 versus 34.1 in the Noometry coding category.
How many benchmarks do Gemma 2 27B and o1-mini share?
29 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and o1-mini has 39.