Model comparison
Gemini 2.0 Flash-Lite vs gpt-oss-120b
Gemini 2.0 Flash-Lite is the stronger model overall, scoring 37.8 to 36.3 on the Noometry Index.
Last verified . 23 shared benchmarks.
GoogleSummary
- They share 23 benchmarks with published results for both. Gemini 2.0 Flash-Lite scores higher in 5 categories and gpt-oss-120b in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 34.1.
- The biggest single-benchmark swing is Omni-MATH: 37.4% for Gemini 2.0 Flash-Lite and 68.8% for gpt-oss-120b.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash-Lite | gpt-oss-120b | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 37.8 | 36.3 |
| Released | 2025-02-05 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 41K |
| Input $ / M tokens | — | $0.037 |
| Output $ / M tokens | — | $0.17 |
| Results tracked | 32 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 37.9 (#185), gpt-oss-120b: 33.5 (#256)
| Benchmark | Gemini 2.0 Flash-Lite | gpt-oss-120b |
|---|---|---|
| LMArena Coding | 1322 | 1380 |
| SWE-bench Verified (bash only) | — | 26% |
| Aider Polyglot | — | 41.8% |
| SciCode | — | 36% |
| WeirdML | — | 48.2% |
| LiveBench Coding | 47.1% | — |
| ALE-Bench | — | 575.62 |
| AlgoTune | — | 1.41 |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash-Lite: —, gpt-oss-120b: 12.2 (#153)
| Benchmark | Gemini 2.0 Flash-Lite | gpt-oss-120b |
|---|---|---|
| Terminal-Bench | — | 18.7% |
| APEX-Agents | — | 4.4% |
| METR Time Horizons | — | 56.6% |
| Vending-Bench 2 | — | -21.53 |
Reasoning Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 22.0 (#210), gpt-oss-120b: 20.0 (#245)
| Benchmark | Gemini 2.0 Flash-Lite | gpt-oss-120b |
|---|---|---|
| LMArena Hard Prompts | 1324 | 1364 |
| DTBench | 52.5% | 76.3% |
| SimpleBench | — | 22.1% |
| Kagi LLM Benchmark | — | 58.6% |
| CritPt | — | 1.1% |
| Chess Puzzles | — | 20% |
| LiveBench Reasoning | 50.1% | — |
| Mystery Game Puzzles | — | 2% |
| LiveBench Data Analysis | 65.5% | — |
| LMCA | — | 22.1% |
| Surface Evolver Bench | — | 25% |
| Epoch Capabilities Index | — | 139.93 |
| ForecastBench | 57.1 | — |
| LiveBench | 54.3% | — |
Math gpt-oss-120b leads
Gemini 2.0 Flash-Lite: 34.1 (#196), gpt-oss-120b: 52.5 (#50)
| Benchmark | Gemini 2.0 Flash-Lite | gpt-oss-120b |
|---|---|---|
| Omni-MATH | 37.4% | 68.8% |
| LMArena Math | 1309 | 1389 |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| LiveBench Math | 58.1% | — |
Knowledge gpt-oss-120b leads
Gemini 2.0 Flash-Lite: 35.0 (#189), gpt-oss-120b: 42.4 (#96)
| Benchmark | Gemini 2.0 Flash-Lite | gpt-oss-120b |
|---|---|---|
| MMLU-Pro | 72% | 79.5% |
| GPQA (HELM) | 50% | 68.4% |
| LMArena Expert | 1305 | 1356 |
| GPQA Diamond | — | 75.8% |
| Confabulations | — | 15.7% |
| Vectara Hallucination Rate | — | 14.2% |
Multimodal Not comparable
Gemini 2.0 Flash-Lite: 31.2 (#109), gpt-oss-120b: —
| Benchmark | Gemini 2.0 Flash-Lite | gpt-oss-120b |
|---|---|---|
| LMArena Vision | 1100 | — |
Multilingual gpt-oss-120b leads
Gemini 2.0 Flash-Lite: 46.0 (#161), gpt-oss-120b: 48.0 (#147)
| Benchmark | Gemini 2.0 Flash-Lite | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1323 | 1351 |
| LMArena Chinese | 1339 | 1385 |
| LMArena French | 1347 | 1369 |
| LMArena German | 1306 | 1353 |
| LMArena Japanese | 1301 | 1331 |
| LMArena Korean | 1325 | 1282 |
| LMArena Russian | 1328 | 1343 |
| LMArena Spanish | 1313 | 1389 |
Instruction Following Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 70.4 (#163), gpt-oss-120b: 69.3 (#173)
| Benchmark | Gemini 2.0 Flash-Lite | gpt-oss-120b |
|---|---|---|
| IFEval | 82.4% | 83.6% |
| LMArena Instruction Following | 1305 | 1318 |
| LiveBench Instruction Following | 78.3% | — |
Long Context Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 40.1 (#160), gpt-oss-120b: 31.4 (#278)
| Benchmark | Gemini 2.0 Flash-Lite | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1320 | 1319 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 51.7 (#177), gpt-oss-120b: 46.5 (#217)
| Benchmark | Gemini 2.0 Flash-Lite | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1330 | 1365 |
| LMArena Creative Writing | 1319 | 1275 |
| WildBench | 79% | 84.5% |
| LMArena Multi-Turn | 1307 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| EQ-Bench Creative Writing | — | 961 |
| LiveBench Language | 34.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash-Lite better than gpt-oss-120b?
Gemini 2.0 Flash-Lite is the stronger model overall, scoring 37.8 to 36.3 on the Noometry Index.
Is Gemini 2.0 Flash-Lite or gpt-oss-120b better for coding?
Gemini 2.0 Flash-Lite scores higher on coding benchmarks: 37.9 versus 33.5 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash-Lite and gpt-oss-120b share?
23 benchmarks have published results for both models. Gemini 2.0 Flash-Lite has 32 scored results on Noometry and gpt-oss-120b has 48.