Xentir Gemini 2.5 Flash (Apr 2025) vs gpt-oss-120b
Gemini 2.5 Flash (Apr 2025) · Google DeepMind, released 2025-04-17
gpt-oss-120b OPEN WEIGHTS · OpenAI, released 2025-08-05
“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-09-09 · Methodology · Data Sources
gpt-oss-120b leads on more of the 2 benchmarks where both are measured — gpt-oss-120b on 2. The remaining 7 of 9 tracked benchmarks cannot be compared: 2 have a result for only one of the two models, 5 for neither. Nothing on this page is estimated to fill those in.
Head-to-head
Measured on 2 of 9 tracked benchmarks for both models — gpt-oss-120b leads on 2.
| Benchmark | Gemini 2.5 Flash (Apr 2025) | gpt-oss-120b | Leads |
|---|---|---|---|
| Epoch Capabilities Index (ECI) | 140.0 | 140.1 | gpt-oss-120b |
| SWE-bench Verified | Not measured | Not measured | Not measured on both |
| GPQA Diamond | Not measured | 0.758 (high-openai) | Comparison unavailable — Gemini 2.5 Flash (Apr 2025) has no published result |
| MATH Level 5 | Not measured | Not measured | Not measured on both |
| OTIS Mock AIME 2024-2025 | 0.731 | 0.889 (high-openai) | gpt-oss-120b |
| FrontierMath | Not measured | Not measured | Not measured on both |
| FrontierMath Tier 4 | Not measured | Not measured | Not measured on both |
| SimpleQA Verified | Not measured | Not measured | Not measured on both |
| Chess Puzzles | Not measured | 0.200 (high-openai) | Comparison unavailable — Gemini 2.5 Flash (Apr 2025) has no published result |
What remains uncertain
- Gemini 2.5 Flash (Apr 2025) has no published result on Chess Puzzles, GPQA Diamond.
- 5 tracked benchmarks have no published result for either model.
A missing result means Xentir has not found one published by the source it cites, not that the model performs badly. See Data Sources.
Full profiles
Gemini 2.5 Flash (Apr 2025) → · gpt-oss-120b → · the full AI Model Rankings table