Model comparison
Gemini 2.5 Flash vs gpt-oss-120b
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 36.3 on the Noometry Index. gpt-oss-120b costs 12× less per token, which makes it the better buy when Gemini 2.5 Flash's lead doesn't matter for your workload.
Last verified . 40 shared benchmarks.
GoogleSummary
- They share 40 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 6 categories and gpt-oss-120b in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Gemini 2.5 Flash leads 30.8 to 12.2.
- The biggest single-benchmark swing is Fiction.LiveBench: 77.8% for Gemini 2.5 Flash and 44.4% for gpt-oss-120b.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.30 / $2.50 for Gemini 2.5 Flash.
- Gemini 2.5 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 2.5 Flash | gpt-oss-120b | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 39.3 | 36.3 |
| Released | 2025-04-17 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 66K | 41K |
| Input $ / M tokens | $0.30 | $0.037 |
| Output $ / M tokens | $2.50 | $0.17 |
| Results tracked | 54 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Flash leads
Gemini 2.5 Flash: 35.8 (#220), gpt-oss-120b: 33.5 (#256)
| Benchmark | Gemini 2.5 Flash | gpt-oss-120b |
|---|---|---|
| SWE-bench Verified (bash only) | 28.7% | 26% |
| Aider Polyglot | 55.1% | 41.8% |
| WeirdML | 41.9% | 48.2% |
| LMArena Coding | 1424 | 1380 |
| ALE-Bench | 661.88 | 575.62 |
| SciCode | — | 36% |
| AlgoTune | — | 1.41 |
Agentic & Tool Use Gemini 2.5 Flash leads
Gemini 2.5 Flash: 30.8 (#74), gpt-oss-120b: 12.2 (#153)
| Benchmark | Gemini 2.5 Flash | gpt-oss-120b |
|---|---|---|
| Terminal-Bench | 17.1% | 18.7% |
| Vending-Bench 2 | 548.84 | -21.53 |
| APEX-Agents | — | 4.4% |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| METR Time Horizons | — | 56.6% |
Reasoning gpt-oss-120b leads
Gemini 2.5 Flash: 18.1 (#286), gpt-oss-120b: 20.0 (#245)
| Benchmark | Gemini 2.5 Flash | gpt-oss-120b |
|---|---|---|
| SimpleBench | 41.2% | 22.1% |
| Kagi LLM Benchmark | 56.8% | 58.6% |
| CritPt | 1.1% | 1.1% |
| LMArena Hard Prompts | 1422 | 1364 |
| DTBench | 76.5% | 76.3% |
| LMCA | 27.5% | 22.1% |
| Epoch Capabilities Index | 143.03 | 139.93 |
| ARC-AGI-2 | 2.5% | — |
| ARC-AGI-1 | 33.3% | — |
| Chess Puzzles | — | 20% |
| EnigmaEval | 2.7% | — |
| Mystery Game Puzzles | — | 2% |
| Surface Evolver Bench | — | 25% |
| ForecastBench | 60.6 | — |
Math gpt-oss-120b leads
Gemini 2.5 Flash: 39.9 (#98), gpt-oss-120b: 52.5 (#50)
| Benchmark | Gemini 2.5 Flash | gpt-oss-120b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 88.9% |
| Omni-MATH | 38.5% | 68.8% |
| LMArena Math | 1415 | 1389 |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge gpt-oss-120b leads
Gemini 2.5 Flash: 36.4 (#168), gpt-oss-120b: 42.4 (#96)
| Benchmark | Gemini 2.5 Flash | gpt-oss-120b |
|---|---|---|
| MMLU-Pro | 63.9% | 79.5% |
| Confabulations | 16.8% | 15.7% |
| Vectara Hallucination Rate | 7.8% | 14.2% |
| GPQA (HELM) | 39% | 68.4% |
| LMArena Expert | 1426 | 1356 |
| GPQA Diamond | — | 75.8% |
| Humanity's Last Exam | 12.1% | — |
Multimodal Not comparable
Gemini 2.5 Flash: 41.8 (#32), gpt-oss-120b: —
| Benchmark | Gemini 2.5 Flash | gpt-oss-120b |
|---|---|---|
| LMArena Vision | 1253 | — |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Gemini 2.5 Flash leads
Gemini 2.5 Flash: 52.3 (#88), gpt-oss-120b: 48.0 (#147)
| Benchmark | Gemini 2.5 Flash | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1409 | 1351 |
| LMArena Chinese | 1450 | 1385 |
| LMArena French | 1433 | 1369 |
| LMArena German | 1418 | 1353 |
| LMArena Japanese | 1405 | 1331 |
| LMArena Korean | 1385 | 1282 |
| LMArena Russian | 1415 | 1343 |
| LMArena Spanish | 1421 | 1389 |
Instruction Following Gemini 2.5 Flash leads
Gemini 2.5 Flash: 75.7 (#54), gpt-oss-120b: 69.3 (#173)
| Benchmark | Gemini 2.5 Flash | gpt-oss-120b |
|---|---|---|
| IFEval | 89.8% | 83.6% |
| LMArena Instruction Following | 1405 | 1318 |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#17), gpt-oss-120b: 31.4 (#278)
| Benchmark | Gemini 2.5 Flash | gpt-oss-120b |
|---|---|---|
| Fiction.LiveBench | 77.8% | 44.4% |
| LMArena Longer Query | 1419 | 1319 |
Writing & Preference Gemini 2.5 Flash leads
Gemini 2.5 Flash: 53.8 (#157), gpt-oss-120b: 46.5 (#217)
| Benchmark | Gemini 2.5 Flash | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1417 | 1365 |
| LMArena Creative Writing | 1400 | 1275 |
| Short-Story Creative Writing | 76.5% | 77.1% |
| EQ-Bench Creative Writing | 1137 | 961 |
| WildBench | 81.7% | 84.5% |
| LMArena Multi-Turn | 1408 | 1340 |
Frequently asked questions
Is Gemini 2.5 Flash better than gpt-oss-120b?
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 36.3 on the Noometry Index. gpt-oss-120b costs 12× less per token, which makes it the better buy when Gemini 2.5 Flash's lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 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 2.5 Flash lists at $0.30 and $2.50.
Is Gemini 2.5 Flash or gpt-oss-120b better for coding?
Gemini 2.5 Flash scores higher on coding benchmarks: 35.8 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 131K.
How many benchmarks do Gemini 2.5 Flash and gpt-oss-120b share?
40 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and gpt-oss-120b has 48.