# Gemini 3.5 Flash vs gpt-oss-120b

> Gemini 3.5 Flash is the stronger model overall, scoring 54.2 to 36.3 on the Noometry Index. gpt-oss-120b costs 48× less per token, which makes it the better buy when Gemini 3.5 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-5-flash-vs-gpt-oss-120b
- Last updated: 2026-10-12
- Shared benchmarks: 32

## Summary

- They share 32 benchmarks with published results for both. Gemini 3.5 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 3.5 Flash leads 62.8 to 20.0.
- The biggest single-benchmark swing is SimpleBench: 76.7% for Gemini 3.5 Flash and 22.1% for gpt-oss-120b.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $1.50 / $9 for Gemini 3.5 Flash.
- Gemini 3.5 Flash accepts more context: 1.05M tokens versus 131K.
- gpt-oss-120b has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.5 Flash | gpt-oss-120b |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 54.2 | 36.3 |
| Rank | 32 | 217 |
| Context | 1.05M | 131K |
| Input $/M | $1.50 | $0.037 |
| Output $/M | $9 | $0.17 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.5 Flash: 49.4 (#49)
- gpt-oss-120b: 33.5 (#256)

| Benchmark | Gemini 3.5 Flash | gpt-oss-120b |
|---|---|---|
| SciCode | 53.1% | 36% |
| WeirdML | 62.6% | 48.2% |
| LMArena Coding | 1492 | 1380 |
| ALE-Bench | 911.02 | 575.62 |
| SWE-bench Verified | 79.3% | — |
| DeepSWE | 37.4% | — |
| SWE-bench Verified (bash only) | — | 26% |
| Aider Polyglot | — | 41.8% |
| LMArena WebDev | 1499 | — |
| AlgoTune | — | 1.41 |

## Agentic & Tool Use

- Gemini 3.5 Flash: 24.7 (#114)
- gpt-oss-120b: 12.2 (#153)

| Benchmark | Gemini 3.5 Flash | gpt-oss-120b |
|---|---|---|
| APEX-Agents | 27.5% | 4.4% |
| Vending-Bench 2 | 5,396 | -21.53 |
| Terminal-Bench | — | 18.7% |
| GBAEval | 6.7% | — |
| GDP.pdf | 14% | — |
| METR Time Horizons | — | 56.6% |

## Reasoning

- Gemini 3.5 Flash: 62.8 (#18)
- gpt-oss-120b: 20.0 (#245)

| Benchmark | Gemini 3.5 Flash | gpt-oss-120b |
|---|---|---|
| SimpleBench | 76.7% | 22.1% |
| CritPt | 13.1% | 1.1% |
| Chess Puzzles | 50% | 20% |
| LMArena Hard Prompts | 1488 | 1364 |
| Mystery Game Puzzles | 32% | 2% |
| DTBench | 94.7% | 76.3% |
| LMCA | 47.1% | 22.1% |
| Surface Evolver Bench | 58.1% | 25% |
| Epoch Capabilities Index | 154.46 | 139.93 |
| ARC-AGI-2 | 72.1% | — |
| Kagi LLM Benchmark | — | 58.6% |
| NYT Connections (extended) | 92.6% | — |
| ARC-AGI-1 | 92.5% | — |
| EnigmaEval | 25.4% | — |
| EBR-Bench | 4.8% | — |
| ForecastBench | 59 | — |

## Math

- Gemini 3.5 Flash: 60.7 (#36)
- gpt-oss-120b: 52.5 (#50)

| Benchmark | Gemini 3.5 Flash | gpt-oss-120b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 88.9% |
| LMArena Math | 1504 | 1389 |
| FrontierMath (Tiers 1-3) | 62.8% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.3% | — |
| ProofBench | 31% | — |
| Omni-MATH | — | 68.8% |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |

## Knowledge

- Gemini 3.5 Flash: 66.3 (#11)
- gpt-oss-120b: 42.4 (#96)

| Benchmark | Gemini 3.5 Flash | gpt-oss-120b |
|---|---|---|
| GPQA Diamond | 92.8% | 75.8% |
| LMArena Expert | 1495 | 1356 |
| SimpleQA Verified | 66.2% | — |
| MMLU-Pro | — | 79.5% |
| Confabulations | — | 15.7% |
| Vectara Hallucination Rate | — | 14.2% |
| GPQA (HELM) | — | 68.4% |

## Multimodal

- Gemini 3.5 Flash: 45.7 (#15)
- gpt-oss-120b: —

| Benchmark | Gemini 3.5 Flash | gpt-oss-120b |
|---|---|---|
| LMArena Vision | 1310 | — |
| Blueprint-Bench 2 | 33.6% | — |
| LMArena Document | 1463 | — |

## Multilingual

- Gemini 3.5 Flash: 57.0 (#13)
- gpt-oss-120b: 48.0 (#147)

| Benchmark | Gemini 3.5 Flash | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1476 | 1351 |
| LMArena Chinese | 1526 | 1385 |
| LMArena French | 1490 | 1369 |
| LMArena German | 1492 | 1353 |
| LMArena Japanese | 1486 | 1331 |
| LMArena Korean | 1451 | 1282 |
| LMArena Russian | 1493 | 1343 |
| LMArena Spanish | 1480 | 1389 |

## Instruction Following

- Gemini 3.5 Flash: 77.0 (#30)
- gpt-oss-120b: 69.3 (#173)

| Benchmark | Gemini 3.5 Flash | gpt-oss-120b |
|---|---|---|
| LMArena Instruction Following | 1467 | 1318 |
| IFEval | — | 83.6% |

## Long Context

- Gemini 3.5 Flash: 45.4 (#38)
- gpt-oss-120b: 31.4 (#278)

| Benchmark | Gemini 3.5 Flash | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1482 | 1319 |
| Fiction.LiveBench | — | 44.4% |

## Writing & Preference

- Gemini 3.5 Flash: 65.5 (#47)
- gpt-oss-120b: 46.5 (#217)

| Benchmark | Gemini 3.5 Flash | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1482 | 1365 |
| LMArena Creative Writing | 1470 | 1275 |
| LMArena Multi-Turn | 1481 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| EQ-Bench Creative Writing | — | 961 |
| WildBench | — | 84.5% |
| EQ-Bench 4 | 1087 | — |

## FAQ

### Is Gemini 3.5 Flash better than gpt-oss-120b?

Gemini 3.5 Flash is the stronger model overall, scoring 54.2 to 36.3 on the Noometry Index. gpt-oss-120b costs 48× less per token, which makes it the better buy when Gemini 3.5 Flash's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3.5 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 3.5 Flash lists at $1.50 and $9.

### Is Gemini 3.5 Flash or gpt-oss-120b better for coding?

Gemini 3.5 Flash scores higher on coding benchmarks: 49.4 versus 33.5 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.5 Flash does, with 1.05M tokens against 131K.

### How many benchmarks do Gemini 3.5 Flash and gpt-oss-120b share?

32 benchmarks have published results for both models. Gemini 3.5 Flash has 54 scored results on Noometry and gpt-oss-120b has 48.