Rankings / OpenAI
GPT 4.1 Nano (2025-04-14)
released 2025-04-14
BenchAtlas Index
as of 2026-09-11
high effort
rank #446
8 families · 4 categories · medium
base configuration
rank #450
15 families · 6 categories · high
Benchmark evidence
59 results
agentic coding
| τ²-Bench | 17.3 % | independent | Artificial Analysis | |
| τ²-Bench subset=banking | 3.5 % | independent | Artificial Analysis |
coding
| LiveCodeBench v6 implementation=artificial-analysis | 32.6 % | independent | Artificial Analysis | |
| SciCode | 25.9 % | independent | Artificial Analysis |
external indices
| AA Coding Index | 11.1 points | independent | Artificial Analysis | |
| Intelligence Index v4.1 | 7.8 points | independent | Artificial Analysis | |
| AA Math Index | 24.0 points | independent | Artificial Analysis | |
| ECI | 129.6 points | independent | Epoch AI Benchmarking Hub |
factuality
| MASK contamination=Potential contamination warning: This model was evaluated after the public release of MASK, allowing model builder access to the prompts and solutions. | 61.4 % 59.6–63.2 | independent | Scale Labs | |
| SimpleQA Verified | 6.0 % | independent | Epoch AI Benchmarking Hub 2026-08-31 |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1373.6 1354.3–1392.9 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1362.0 1347.2–1376.7 | community | LMArena Leaderboard Dataset | |
| Industry Life And Physical And Social Science (style control)older version arena=text · category=industry_life_and_physical_and_social_science · style_control=true | 1349.4 1332.9–1366.0 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1339.7 1329.8–1349.7 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1338.5 1321.3–1355.7 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1332.5 1318.9–1346.1 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1324.9 1304.9–1345.0 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1322.1 1314.4–1329.8 | community | LMArena Leaderboard Dataset | |
| Industry Business And Management And Financial Operations (style control)older version arena=text · category=industry_business_and_management_and_financial_operations · style_control=true | 1321.3 1299.2–1343.3 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1314.4 1296.3–1332.4 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1306.5 1288.1–1325.0 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1300.4 1287.9–1312.9 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1299.4 1278.6–1320.1 | community | LMArena Leaderboard Dataset | |
| Industry Writing And Literature And Language (style control)older version arena=text · category=industry_writing_and_literature_and_language · style_control=true | 1298.8 1284.5–1313.1 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1297.3 1286.2–1308.5 | community | LMArena Leaderboard Dataset | |
| Industry Entertainment And Sports And Media (style control)older version arena=text · category=industry_entertainment_and_sports_and_media · style_control=true | 1286.6 1269.3–1303.8 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1279.5 1255.5–1303.5 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1273.6 1250.6–1296.7 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1266.4 1254.1–1278.7 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | 51.2 % | independent | Artificial Analysis | |
| GPQA Diamond implementation=vals-ai | high effort | 50.8 % | independent | Vals AI |
| GPQA Diamond | 48.9 % | independent | Epoch AI Benchmarking Hub 2025-04-14 | |
| Humanity's Last Exam implementation=artificial-analysis | 3.8 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=artificial-analysis | 65.7 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=vals-ai | high effort | 63.5 % | independent | Vals AI |
long context instruction
| AA-LCR | 20.3 % | independent | Artificial Analysis | |
| IFBench | 32.0 % | independent | Artificial Analysis |
multimodal
| MMMU implementation=vals-ai | high effort | 55.1 % | independent | Vals AI |
| VISTA | 26.6 % 26.2–26.9 | independent | Scale Labs |
professional
| CorpFin | high effort | 42.1 % | independent | Vals AI |
| LegalBench | high effort | 61.1 % | independent | Vals AI |
| MedQA | high effort | 68.2 % | independent | Vals AI |
| TaxEval | high effort | 60.8 % | independent | Vals AI |
reasoning math
| AIME implementation=vals-ai | high effort | 26.5 % | independent | Vals AI |
| AIME year=2025 · implementation=artificial-analysis | 24.0 % | independent | Artificial Analysis | |
| AIME implementation=artificial-analysis | 23.7 % | independent | Artificial Analysis | |
| ARC-AGI-1older version split=public_eval · model_type=Base LLM | 1.8 % | independent | ARC Prize Leaderboard | |
| ARC-AGI-2 split=semi_private · model_type=Base LLM | 0.0 usd_per_task | independent | ARC Prize Leaderboard | |
| ARC-AGI-2 split=public_eval · model_type=Base LLM | 0.0 usd_per_task | independent | ARC Prize Leaderboard | |
| ARC-AGI-1older version split=semi_private · model_type=Base LLM | 0.0 usd_per_task | independent | ARC Prize Leaderboard | |
| ARC-AGI-1older version split=public_eval · model_type=Base LLM | 0.0 usd_per_task | independent | ARC Prize Leaderboard | |
| ARC-AGI-1older version split=semi_private · model_type=Base LLM | 0.0 % | independent | ARC Prize Leaderboard | |
| ARC-AGI-2 split=semi_private · model_type=Base LLM | 0.0 % | independent | ARC Prize Leaderboard | |
| ARC-AGI-2 split=public_eval · model_type=Base LLM | 0.0 % | independent | ARC Prize Leaderboard | |
| FrontierMath | 1.0 % | independent | Epoch AI Benchmarking Hub 2025-04-14 | |
| MATH-500 implementation=artificial-analysis | 84.8 % | independent | Artificial Analysis | |
| MATH-500 implementation=vals-ai | high effort | 80.2 % | independent | Vals AI |
| MATH Level 5 | 70.0 % | independent | Epoch AI Benchmarking Hub 2025-04-14 | |
| OTIS Mock AIME 2024–2025 | 28.9 % | independent | Epoch AI Benchmarking Hub 2025-04-14 |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + GPT 4.1 Nano (2025-04-14) | Terminal-Bench Hard | 3.8 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + GPT 4.1 Nano (2025-04-14) | Terminal-Bench 2.1 | 3.8 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.