OpenAI
GPT-4.1 nano benchmark results
7 results on 6 benchmarks from 3 sources.
Also listed as: gpt-4.1-nano-2025-04-14 · GPT-4.1-nano-2025-04-14 (FC) · GPT-4.1-nano-2025-04-14 (Prompt)
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1322 | 255 | Overall, style control on; 6103 votes; 95% CI 1315–1330“gpt-4.1-nano-2025-04-14” | Official leaderboard | Oct 8, 2026 |
| LMArena Vision | 1089 | 131 | Overall, style control on; 1211 votes; 95% CI 1070–1107“gpt-4.1-nano-2025-04-14” | Official leaderboard | Oct 2, 2026 |
| GPQA Diamond | 48.9% | 209 | Epoch AI run, accuracy | Independent run | Apr 14, 2025 |
| AIME (OTIS Mock AIME 2024–2025) | 28.9% | 194 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Apr 14, 2025 |
| MATH Level 5 | 70.0% | 42 | Epoch AI run, accuracy | Independent run | Apr 14, 2025 |
| BFCL v4 (function calling) | 33.0% | 58 | Overall accuracy; native function calling (FC)“GPT-4.1-nano-2025-04-14 (FC)” | Official leaderboard | Oct 17, 2026 |
| BFCL v4 (function calling) | 24.9% | 90 | Overall accuracy; prompt-based“GPT-4.1-nano-2025-04-14 (Prompt)” | Official leaderboard | Oct 17, 2026 |
FAQ
Where do these GPT-4.1 nano scores come from?
From Epoch AI Benchmarking Hub, Berkeley Function Calling Leaderboard (BFCL), and LMArena leaderboard dataset. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.