Model comparison
Gemma 2 27B vs gpt-oss-120b
gpt-oss-120b is the stronger model overall, scoring 36.3 to 29.4 on the Noometry Index.
Last verified . 23 shared benchmarks.
GoogleSummary
- They share 23 benchmarks with published results for both. Gemma 2 27B scores higher in 2 categories and gpt-oss-120b in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 10.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.4% for Gemma 2 27B and 88.9% for gpt-oss-120b.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
- gpt-oss-120b accepts more context: 131K tokens versus 8K.
Side by side
| Gemma 2 27B | gpt-oss-120b | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 29.4 | 36.3 |
| Released | 2024-06-24 | 2025-08-05 |
| Weights | Open | Open |
| Context window | 8K | 131K |
| Max output | 2K | 41K |
| Input $ / M tokens | $0.65 | $0.037 |
| Output $ / M tokens | $0.65 | $0.17 |
| Results tracked | 34 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 2 27B: 34.1 (#246), gpt-oss-120b: 33.5 (#256)
| Benchmark | Gemma 2 27B | gpt-oss-120b |
|---|---|---|
| LMArena Coding | 1211 | 1380 |
| SWE-bench Verified (bash only) | — | 26% |
| Aider Polyglot | — | 41.8% |
| SciCode | — | 36% |
| WeirdML | — | 48.2% |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | — | 575.62 |
| AlgoTune | — | 1.41 |
Agentic & Tool Use Not comparable
Gemma 2 27B: —, gpt-oss-120b: 12.2 (#153)
| Benchmark | Gemma 2 27B | gpt-oss-120b |
|---|---|---|
| Terminal-Bench | — | 18.7% |
| APEX-Agents | — | 4.4% |
| METR Time Horizons | — | 56.6% |
| Vending-Bench 2 | — | -21.53 |
Reasoning gpt-oss-120b leads
Gemma 2 27B: 15.3 (#315), gpt-oss-120b: 20.0 (#245)
| Benchmark | Gemma 2 27B | gpt-oss-120b |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1364 |
| DTBench | 48% | 76.3% |
| LMCA | 7.1% | 22.1% |
| Epoch Capabilities Index | 122.08 | 139.93 |
| SimpleBench | — | 22.1% |
| Kagi LLM Benchmark | — | 58.6% |
| CritPt | — | 1.1% |
| Chess Puzzles | — | 20% |
| LiveBench Reasoning | 28.1% | — |
| Mystery Game Puzzles | — | 2% |
| LiveBench Data Analysis | 47.9% | — |
| Surface Evolver Bench | — | 25% |
| LiveBench | 38.2% | — |
Math gpt-oss-120b leads
Gemma 2 27B: 10.7 (#311), gpt-oss-120b: 52.5 (#50)
| Benchmark | Gemma 2 27B | gpt-oss-120b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.4% | 88.9% |
| LMArena Math | 1212 | 1389 |
| Omni-MATH | — | 68.8% |
| LiveBench Math | 26.5% | — |
| MATH Level 5 | 27.9% | — |
Knowledge gpt-oss-120b leads
Gemma 2 27B: 19.0 (#280), gpt-oss-120b: 42.4 (#96)
| Benchmark | Gemma 2 27B | gpt-oss-120b |
|---|---|---|
| GPQA Diamond | 36.5% | 75.8% |
| Confabulations | 27.1% | 15.7% |
| LMArena Expert | 1172 | 1356 |
| MMLU-Pro | — | 79.5% |
| Vectara Hallucination Rate | — | 14.2% |
| GPQA (HELM) | — | 68.4% |
| MMLU | 75.7% | — |
Multilingual gpt-oss-120b leads
Gemma 2 27B: 38.6 (#226), gpt-oss-120b: 48.0 (#147)
| Benchmark | Gemma 2 27B | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1217 | 1351 |
| LMArena Chinese | 1221 | 1385 |
| LMArena French | 1247 | 1369 |
| LMArena German | 1209 | 1353 |
| LMArena Japanese | 1175 | 1331 |
| LMArena Korean | 1174 | 1282 |
| LMArena Russian | 1234 | 1343 |
| LMArena Spanish | 1228 | 1389 |
Instruction Following gpt-oss-120b leads
Gemma 2 27B: 60.5 (#249), gpt-oss-120b: 69.3 (#173)
| Benchmark | Gemma 2 27B | gpt-oss-120b |
|---|---|---|
| LMArena Instruction Following | 1206 | 1318 |
| LiveBench Instruction Following | 58.1% | — |
| IFEval | — | 83.6% |
Long Context Gemma 2 27B leads
Gemma 2 27B: 37.3 (#218), gpt-oss-120b: 31.4 (#278)
| Benchmark | Gemma 2 27B | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1231 | 1319 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference gpt-oss-120b leads
Gemma 2 27B: 44.2 (#225), gpt-oss-120b: 46.5 (#217)
| Benchmark | Gemma 2 27B | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1231 | 1365 |
| LMArena Creative Writing | 1241 | 1275 |
| LMArena Multi-Turn | 1224 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| EQ-Bench Creative Writing | — | 961 |
| WildBench | — | 84.5% |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than gpt-oss-120b?
gpt-oss-120b is the stronger model overall, scoring 36.3 to 29.4 on the Noometry Index.
Which is cheaper, Gemma 2 27B or gpt-oss-120b?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Gemma 2 27B lists at $0.65 and $0.65.
Is Gemma 2 27B or gpt-oss-120b better for coding?
They score almost the same on coding (34.1 vs 33.5); test both on your own repository before choosing.
Which has the bigger context window?
gpt-oss-120b does, with 131K tokens against 8K.
How many benchmarks do Gemma 2 27B and gpt-oss-120b share?
23 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and gpt-oss-120b has 48.