Model comparison
Gemma 3 12B vs gpt-oss-120b
gpt-oss-120b is the stronger model overall, scoring 36.0 to 31.8 on the Noometry Index.
Last verified . 22 shared benchmarks.
GoogleSummary
- They share 22 benchmarks with published results for both. Gemma 3 12B scores higher in 3 categories and gpt-oss-120b in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 50.6 to 21.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.7% for Gemma 3 12B and 88.9% for gpt-oss-120b.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.05 / $0.15 for Gemma 3 12B.
Side by side
| Gemma 3 12B | gpt-oss-120b | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 31.8 | 36.0 |
| Released | 2025-03-12 | 2025-08-05 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 8K | 41K |
| Input $ / M tokens | $0.05 | $0.037 |
| Output $ / M tokens | $0.15 | $0.17 |
| Results tracked | 24 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-120b leads
Gemma 3 12B: 31.2 (#276), gpt-oss-120b: 33.2 (#251)
| Benchmark | Gemma 3 12B | gpt-oss-120b |
|---|---|---|
| SciCode | 17.4% | 36% |
| LMArena Coding | 1281 | 1380 |
| SWE-bench Verified (bash only) | — | 26% |
| Aider Polyglot | — | 41.8% |
| WeirdML | — | 48.2% |
| ALE-Bench | — | 575.62 |
| AlgoTune | — | 1.41 |
Agentic & Tool Use Gemma 3 12B leads
Gemma 3 12B: 25.3 (#101), gpt-oss-120b: 12.1 (#145)
| Benchmark | Gemma 3 12B | gpt-oss-120b |
|---|---|---|
| Terminal-Bench | — | 18.7% |
| APEX-Agents | — | 4.4% |
| Berkeley Function Calling Leaderboard | 30.4% | — |
| METR Time Horizons | — | 56.6% |
| Vending-Bench 2 | — | -21.53 |
Reasoning gpt-oss-120b leads
Gemma 3 12B: 15.2 (#307), gpt-oss-120b: 19.5 (#236)
| Benchmark | Gemma 3 12B | gpt-oss-120b |
|---|---|---|
| CritPt | 0% | 1.1% |
| Chess Puzzles | 0% | 20% |
| LMArena Hard Prompts | 1309 | 1364 |
| DTBench | 48.8% | 76.3% |
| LMCA | 4.5% | 22.1% |
| Epoch Capabilities Index | 123.49 | 139.94 |
| SimpleBench | — | 22.1% |
| Kagi LLM Benchmark | — | 58.6% |
| Mystery Game Puzzles | — | 2% |
| Surface Evolver Bench | — | 25% |
Math gpt-oss-120b leads
Gemma 3 12B: 21.0 (#273), gpt-oss-120b: 50.6 (#43)
| Benchmark | Gemma 3 12B | gpt-oss-120b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | 88.9% |
| LMArena Math | 1307 | 1388 |
| Omni-MATH | — | 68.8% |
Knowledge gpt-oss-120b leads
Gemma 3 12B: 26.5 (#250), gpt-oss-120b: 42.3 (#89)
| Benchmark | Gemma 3 12B | gpt-oss-120b |
|---|---|---|
| GPQA Diamond | 39.5% | 75.8% |
| Vectara Hallucination Rate | 4.4% | 14.2% |
| LMArena Expert | 1248 | 1356 |
| MMLU-Pro | — | 79.5% |
| Confabulations | — | 15.7% |
| GPQA (HELM) | — | 68.4% |
Multimodal Not comparable
Gemma 3 12B: —, gpt-oss-120b: —
| Benchmark | Gemma 3 12B | gpt-oss-120b |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual gpt-oss-120b leads
Gemma 3 12B: 45.9 (#160), gpt-oss-120b: 48.2 (#142)
| Benchmark | Gemma 3 12B | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1318 | 1350 |
| LMArena German | 1370 | 1355 |
| LMArena Russian | 1335 | 1343 |
| LMArena Chinese | — | 1384 |
| LMArena French | — | 1370 |
| LMArena Japanese | — | 1332 |
| LMArena Korean | — | 1283 |
| LMArena Spanish | — | 1388 |
Instruction Following Too close to call
Gemma 3 12B: 68.8 (#179), gpt-oss-120b: 69.5 (#168)
| Benchmark | Gemma 3 12B | gpt-oss-120b |
|---|---|---|
| LMArena Instruction Following | 1299 | 1318 |
| IFEval | — | 83.6% |
Long Context Gemma 3 12B leads
Gemma 3 12B: 40.0 (#157), gpt-oss-120b: 31.4 (#273)
| Benchmark | Gemma 3 12B | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1317 | 1319 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference Gemma 3 12B leads
Gemma 3 12B: 47.7 (#205), gpt-oss-120b: 46.7 (#213)
| Benchmark | Gemma 3 12B | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1334 | 1366 |
| LMArena Creative Writing | 1331 | 1274 |
| EQ-Bench Creative Writing | 1126 | 961 |
| LMArena Multi-Turn | 1334 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| WildBench | — | 84.5% |
Frequently asked questions
Is Gemma 3 12B better than gpt-oss-120b?
gpt-oss-120b is the stronger model overall, scoring 36.0 to 31.8 on the Noometry Index.
Which is cheaper, Gemma 3 12B 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 3 12B lists at $0.05 and $0.15.
Is Gemma 3 12B or gpt-oss-120b better for coding?
gpt-oss-120b scores higher on coding benchmarks: 33.2 versus 31.2 in the Noometry coding category.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do Gemma 3 12B and gpt-oss-120b share?
22 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and gpt-oss-120b has 48.