Model comparison
Gemini 2.0 Flash (Feb 2025) vs gpt-oss-120b
gpt-oss-120b is the stronger model overall, scoring 36.3 to 35.1 on the Noometry Index.
Last verified . 35 shared benchmarks.
GoogleSummary
- They share 35 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 4 categories and gpt-oss-120b in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Gemini 2.0 Flash (Feb 2025) leads 28.1 to 12.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Gemini 2.0 Flash (Feb 2025) and 88.9% for gpt-oss-120b.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash (Feb 2025) | gpt-oss-120b | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 35.1 | 36.3 |
| Released | 2024-12-06 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 41K |
| Input $ / M tokens | — | $0.037 |
| Output $ / M tokens | — | $0.17 |
| Results tracked | 54 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-120b leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), gpt-oss-120b: 33.5 (#256)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | gpt-oss-120b |
|---|---|---|
| SWE-bench Verified (bash only) | 13.5% | 26% |
| Aider Polyglot | 38.2% | 41.8% |
| WeirdML | 25.8% | 48.2% |
| LMArena Coding | 1350 | 1380 |
| SciCode | — | 36% |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
| ALE-Bench | — | 575.62 |
| AlgoTune | — | 1.41 |
Agentic & Tool Use Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), gpt-oss-120b: 12.2 (#153)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | gpt-oss-120b |
|---|---|---|
| Terminal-Bench | — | 18.7% |
| APEX-Agents | — | 4.4% |
| TheAgentCompany | 11.4% | — |
| METR Time Horizons | — | 56.6% |
| Vending-Bench 2 | — | -21.53 |
Reasoning gpt-oss-120b leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), gpt-oss-120b: 20.0 (#245)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | gpt-oss-120b |
|---|---|---|
| SimpleBench | 31.1% | 22.1% |
| Kagi LLM Benchmark | 37.8% | 58.6% |
| LMArena Hard Prompts | 1346 | 1364 |
| DTBench | 63.2% | 76.3% |
| Epoch Capabilities Index | 135.36 | 139.93 |
| ARC-AGI-2 | 1.3% | — |
| CritPt | — | 1.1% |
| Chess Puzzles | — | 20% |
| EnigmaEval | 1.1% | — |
| LiveBench Reasoning | 78.2% | — |
| Mystery Game Puzzles | — | 2% |
| LiveBench Data Analysis | 69.4% | — |
| LMCA | — | 22.1% |
| Surface Evolver Bench | — | 25% |
| LiveBench | 66.9% | — |
Math gpt-oss-120b leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), gpt-oss-120b: 52.5 (#50)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | gpt-oss-120b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 88.9% |
| Omni-MATH | 45.9% | 68.8% |
| LMArena Math | 1352 | 1389 |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge gpt-oss-120b leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), gpt-oss-120b: 42.4 (#96)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | gpt-oss-120b |
|---|---|---|
| GPQA Diamond | 64.1% | 75.8% |
| MMLU-Pro | 73.7% | 79.5% |
| Confabulations | 12.4% | 15.7% |
| GPQA (HELM) | 55.6% | 68.4% |
| LMArena Expert | 1339 | 1356 |
| Humanity's Last Exam | 6.6% | — |
| Vectara Hallucination Rate | — | 14.2% |
| MMLU | 79.7% | — |
Multimodal Not comparable
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), gpt-oss-120b: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | gpt-oss-120b |
|---|---|---|
| LMArena Vision | 1158 | — |
| GeoBench | 77% | — |
Multilingual Too close to call
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), gpt-oss-120b: 48.0 (#147)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1342 | 1351 |
| LMArena Chinese | 1373 | 1385 |
| LMArena French | 1391 | 1369 |
| LMArena German | 1353 | 1353 |
| LMArena Japanese | 1294 | 1331 |
| LMArena Korean | 1313 | 1282 |
| LMArena Russian | 1351 | 1343 |
| LMArena Spanish | 1363 | 1389 |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), gpt-oss-120b: 69.3 (#173)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | gpt-oss-120b |
|---|---|---|
| IFEval | 84.1% | 83.6% |
| LMArena Instruction Following | 1336 | 1318 |
| LiveBench Instruction Following | 85.8% | — |
Long Context Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), gpt-oss-120b: 31.4 (#278)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | gpt-oss-120b |
|---|---|---|
| Fiction.LiveBench | 61.1% | 44.4% |
| LMArena Longer Query | 1344 | 1319 |
Writing & Preference Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), gpt-oss-120b: 46.5 (#217)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1354 | 1365 |
| LMArena Creative Writing | 1340 | 1275 |
| Short-Story Creative Writing | 73.8% | 77.1% |
| EQ-Bench Creative Writing | 1128 | 961 |
| WildBench | 80% | 84.5% |
| LMArena Multi-Turn | 1350 | 1340 |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than gpt-oss-120b?
gpt-oss-120b is the stronger model overall, scoring 36.3 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or gpt-oss-120b better for coding?
gpt-oss-120b scores higher on coding benchmarks: 33.5 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and gpt-oss-120b share?
35 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and gpt-oss-120b has 48.