OpenAI
gpt-oss-120b benchmark results
9 results on 6 benchmarks from 4 sources.
Also listed as: openai/gpt-oss-120b_high · gpt-oss-120b_unknown · gpt-oss-120b (unknown thinking) · GPT-OSS-120B · GPT-oss-120B(high)
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1352 | 213 | Overall, style control on; 30218 votes; 95% CI 1347–1356 | Official leaderboard | Oct 8, 2026 |
| GPQA Diamond | 75.8% | 135 | Epoch AI run, accuracy | Independent run | Dec 11, 2025 |
| MMLU-Pro | 80.8% | 61 | Overall accuracy; data source: Self-Reported; 120B“GPT-oss-120B(high)” | Vendor-reported | Mar 11, 2026 |
| SWE-bench Verified | 26.0% | 95 | agent: mini-SWE-agent | Official leaderboard | Aug 7, 2025 |
| AIME (OTIS Mock AIME 2024–2025) | 88.9% | 73 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Dec 11, 2025 |
| Terminal-Bench 2.0 | 18.7% | 167 | Terminal-Bench 2.0; agent: Terminus 2 | Official leaderboard via Epoch AI | Nov 1, 2025 |
| Terminal-Bench 2.0 | 18.7% | 168 | Terminal-Bench 2.0; agent: Terminus 2; effort: unknown thinking | Official leaderboard via Epoch AI | Aug 5, 2025 |
| Terminal-Bench 2.0 | 14.2% | 179 | Terminal-Bench 2.0; agent: Mini-SWE-Agent | Official leaderboard via Epoch AI | Nov 3, 2025 |
| Terminal-Bench 2.0 | 14.2% | 181 | Terminal-Bench 2.0; agent: Mini-SWE-Agent; effort: unknown thinking | Official leaderboard via Epoch AI | Aug 5, 2025 |
Related on this site
FAQ
Where do these gpt-oss-120b scores come from?
From Epoch AI Benchmarking Hub, LMArena leaderboard dataset, MMLU-Pro leaderboard (TIGER-Lab), and SWE-bench leaderboards (swebench.com). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.