OpenAI
o4-mini benchmark results
19 results on 10 benchmarks from 6 sources.
Also listed as: o4-mini-2025-04-16_medium · o4-mini (medium) · o4-mini-2025-04-16_low · o4-mini (low) · o4-mini-2025-04-16_high · o4-mini (high) · o4-mini (high) (April 2025) · o4-mini (medium) (April 2025) · PatchPilot-v1.1 · o4-mini-20250416
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1391 | 172 | Overall, style control on; 44858 votes; 95% CI 1387–1395“o4-mini-2025-04-16” | Official leaderboard | Oct 8, 2026 |
| LMArena Vision | 1201 | 83 | Overall, style control on; 41340 votes; 95% CI 1194–1208“o4-mini-2025-04-16” | Official leaderboard | Oct 2, 2026 |
| LiveCodeBench | 75.8% | 1 | Code generation, 182 problems dated 2025-01-01…2025-04-07“O4-Mini (High)” | Official leaderboard | Apr 7, 2025 |
| GPQA Diamond | 79.6% | 118 | Epoch AI run, accuracy; effort: high | Independent run | Apr 16, 2025 |
| GPQA Diamond | 77.8% | 125 | Epoch AI run, accuracy; effort: medium | Independent run | Aug 7, 2026 |
| GPQA Diamond | 75.3% | 141 | Epoch AI run, accuracy; effort: low | Independent run | Jul 11, 2026 |
| SWE-bench Verified | 64.6% | 40 | agent: PatchPilot-v1.1 | Official leaderboard | May 3, 2025 |
| SWE-bench Verified | 45.0% | 73 | agent: mini-SWE-agent“o4-mini-20250416” | Official leaderboard | Jul 26, 2025 |
| AIME (OTIS Mock AIME 2024–2025) | 81.7% | 107 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: high | Independent run | Apr 16, 2025 |
| AIME (OTIS Mock AIME 2024–2025) | 73.3% | 120 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: medium | Independent run | Aug 7, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 57.8% | 152 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: low | Independent run | Jul 13, 2026 |
| MATH Level 5 | 97.8% | 4 | Epoch AI run, accuracy; effort: high | Independent run | Apr 16, 2025 |
| Humanity's Last Exam | 18.1% | 26 | Compiled by Epoch AI; effort: high | Third-party compilation via Epoch AI | Apr 16, 2025 |
| Humanity's Last Exam | 14.3% | 28 | Compiled by Epoch AI; effort: medium | Third-party compilation via Epoch AI | Apr 16, 2025 |
| τ²-bench | 52.1% | 23 | airline domain, pass^1; submitted by Sierra; v0.1.3 | Official leaderboard | Jun 9, 2025 |
| τ²-bench | 68.3% | 25 | retail domain, pass^1; submitted by Sierra; v0.1.3 | Official leaderboard | Jun 9, 2025 |
| τ²-bench | 50.2% | 18 | telecom domain, pass^1; submitted by Sierra; v0.1.3 | Official leaderboard | Jun 9, 2025 |
| BFCL v4 (function calling) | 53.2% | 21 | Overall accuracy; native function calling (FC)“o4-mini-2025-04-16 (FC)” | Official leaderboard | Oct 17, 2026 |
| BFCL v4 (function calling) | 50.3% | 28 | Overall accuracy; prompt-based“o4-mini-2025-04-16 (Prompt)” | Official leaderboard | Oct 17, 2026 |
FAQ
Where do these o4-mini scores come from?
From Epoch AI Benchmarking Hub, Berkeley Function Calling Leaderboard (BFCL), LiveCodeBench leaderboard, LMArena leaderboard dataset, SWE-bench leaderboards (swebench.com), and τ²-bench leaderboard submissions. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.