Model comparison
Gemini 3.6 Flash vs gpt-oss-120b
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 36.0 on the Noometry Index. gpt-oss-120b costs 21× less per token, which makes it the better buy when Gemini 3.6 Flash's lead doesn't matter for your workload.
Last verified . 30 shared benchmarks.
GoogleSummary
- They share 30 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 9 categories and gpt-oss-120b in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.9 to 19.5.
- The biggest single-benchmark swing is APEX-Agents: 46.9% for Gemini 3.6 Flash and 4.4% for gpt-oss-120b.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.6 Flash.
- Gemini 3.6 Flash accepts more context: 1.05M tokens versus 131K.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.6 Flash | gpt-oss-120b | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 54.1 | 36.0 |
| Released | 2026-07-21 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 66K | 41K |
| Input $ / M tokens | $0.75 | $0.037 |
| Output $ / M tokens | $3.75 | $0.17 |
| Results tracked | 46 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.6 Flash leads
Gemini 3.6 Flash: 49.6 (#45), gpt-oss-120b: 33.2 (#251)
| Benchmark | Gemini 3.6 Flash | gpt-oss-120b |
|---|---|---|
| SciCode | 52.7% | 36% |
| WeirdML | 56.1% | 48.2% |
| LMArena Coding | 1492 | 1380 |
| ALE-Bench | 715.52 | 575.62 |
| DeepSWE | 46.7% | — |
| FrontierCode | 34.4% | — |
| SWE-bench Verified (bash only) | — | 26% |
| Aider Polyglot | — | 41.8% |
| LMArena WebDev | 1536 | — |
| AlgoTune | — | 1.41 |
Agentic & Tool Use Gemini 3.6 Flash leads
Gemini 3.6 Flash: 32.4 (#56), gpt-oss-120b: 12.1 (#145)
| Benchmark | Gemini 3.6 Flash | gpt-oss-120b |
|---|---|---|
| APEX-Agents | 46.9% | 4.4% |
| Terminal-Bench | — | 18.7% |
| GDP.pdf | 14% | — |
| METR Time Horizons | — | 56.6% |
| Vending-Bench 2 | — | -21.53 |
Reasoning Gemini 3.6 Flash leads
Gemini 3.6 Flash: 58.9 (#20), gpt-oss-120b: 19.5 (#236)
| Benchmark | Gemini 3.6 Flash | gpt-oss-120b |
|---|---|---|
| CritPt | 10.6% | 1.1% |
| Chess Puzzles | 43% | 20% |
| LMArena Hard Prompts | 1486 | 1364 |
| Mystery Game Puzzles | 30% | 2% |
| DTBench | 95.5% | 76.3% |
| LMCA | 44.9% | 22.1% |
| Epoch Capabilities Index | 154.36 | 139.94 |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | — | 22.1% |
| Kagi LLM Benchmark | — | 58.6% |
| NYT Connections (extended) | 89% | — |
| ARC-AGI-1 | 91.2% | — |
| Surface Evolver Bench | — | 25% |
Math Gemini 3.6 Flash leads
Gemini 3.6 Flash: 57.0 (#33), gpt-oss-120b: 50.6 (#43)
| Benchmark | Gemini 3.6 Flash | gpt-oss-120b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.2% | 88.9% |
| LMArena Math | 1504 | 1388 |
| FrontierMath (Tiers 1-3) | 58.9% | — |
| FrontierMath Tier 4 | 22% | — |
| MathArena Final-Answer Competitions | 70.8% | — |
| ProofBench | 36% | — |
| Omni-MATH | — | 68.8% |
Knowledge Gemini 3.6 Flash leads
Gemini 3.6 Flash: 67.8 (#7), gpt-oss-120b: 42.3 (#89)
| Benchmark | Gemini 3.6 Flash | gpt-oss-120b |
|---|---|---|
| GPQA Diamond | 94.1% | 75.8% |
| LMArena Expert | 1489 | 1356 |
| SimpleQA Verified | 66.2% | — |
| MMLU-Pro | — | 79.5% |
| Confabulations | — | 15.7% |
| Vectara Hallucination Rate | — | 14.2% |
| GPQA (HELM) | — | 68.4% |
Multimodal Not comparable
Gemini 3.6 Flash: 38.7 (#55), gpt-oss-120b: —
| Benchmark | Gemini 3.6 Flash | gpt-oss-120b |
|---|---|---|
| LMArena Vision | 1297 | — |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 23.3% | — |
| LMArena Document | 1456 | — |
Multilingual Gemini 3.6 Flash leads
Gemini 3.6 Flash: 56.8 (#17), gpt-oss-120b: 48.2 (#142)
| Benchmark | Gemini 3.6 Flash | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1470 | 1350 |
| LMArena Chinese | 1530 | 1384 |
| LMArena French | 1501 | 1370 |
| LMArena German | 1478 | 1355 |
| LMArena Japanese | 1477 | 1332 |
| LMArena Korean | 1435 | 1283 |
| LMArena Russian | 1490 | 1343 |
| LMArena Spanish | 1477 | 1388 |
Instruction Following Gemini 3.6 Flash leads
Gemini 3.6 Flash: 77.2 (#27), gpt-oss-120b: 69.5 (#168)
| Benchmark | Gemini 3.6 Flash | gpt-oss-120b |
|---|---|---|
| LMArena Instruction Following | 1467 | 1318 |
| IFEval | — | 83.6% |
Long Context Gemini 3.6 Flash leads
Gemini 3.6 Flash: 45.1 (#47), gpt-oss-120b: 31.4 (#273)
| Benchmark | Gemini 3.6 Flash | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1475 | 1319 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference Gemini 3.6 Flash leads
Gemini 3.6 Flash: 68.3 (#26), gpt-oss-120b: 46.7 (#213)
| Benchmark | Gemini 3.6 Flash | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1478 | 1366 |
| LMArena Creative Writing | 1464 | 1274 |
| EQ-Bench Creative Writing | 1604 | 961 |
| LMArena Multi-Turn | 1481 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| WildBench | — | 84.5% |
Frequently asked questions
Is Gemini 3.6 Flash better than gpt-oss-120b?
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 36.0 on the Noometry Index. gpt-oss-120b costs 21× less per token, which makes it the better buy when Gemini 3.6 Flash's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.6 Flash 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; Gemini 3.6 Flash lists at $0.75 and $3.75.
Is Gemini 3.6 Flash or gpt-oss-120b better for coding?
Gemini 3.6 Flash scores higher on coding benchmarks: 49.6 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.6 Flash does, with 1.05M tokens against 131K.
How many benchmarks do Gemini 3.6 Flash and gpt-oss-120b share?
30 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and gpt-oss-120b has 48.