Rankings / OpenAI
GPT 4o (2024-05-13)
released 2024-05-13
BenchAtlas Index
as of 2026-09-11
base configuration
rank #335
4 families · 3 categories · medium
Benchmark evidence
34 results
coding
| LiveCodeBench v5older version problems=279 · window_start=2024-08-01 | 32.9 % | independent | LiveCodeBench Leaderboard |
external indices
| ECI | 129.0 points | independent | Epoch AI Benchmarking Hub |
human preference
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1371.7 1361.5–1381.8 | community | LMArena Leaderboard Dataset | |
| Coding (style control)older version arena=text · category=coding · style_control=true | 1369.2 1362.7–1375.6 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1359.9 1354.3–1365.5 | community | LMArena Leaderboard Dataset | |
| French (style control)older version arena=text · category=french · style_control=true | 1359.8 1338.7–1380.8 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1356.2 1351.6–1360.8 | 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 | 1354.0 1347.2–1360.8 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1352.6 1341.9–1363.3 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1347.5 1341.0–1353.9 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1345.8 1342.3–1349.2 | 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 | 1344.6 1338.7–1350.5 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1341.2 1320.9–1361.5 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1340.7 1334.0–1347.3 | community | LMArena Leaderboard Dataset | |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1338.8 1330.1–1347.5 | 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 | 1337.4 1330.5–1344.3 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1337.1 1331.7–1342.5 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1337.1 1329.9–1344.3 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1332.1 1324.6–1339.6 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1331.7 1324.7–1338.7 | community | LMArena Leaderboard Dataset | |
| German (style control)older version arena=text · category=german · style_control=true | 1329.3 1315.9–1342.8 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1329.0 1324.2–1333.8 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1325.3 1320.3–1330.4 | 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 | 1321.4 1313.8–1329.0 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1311.1 1300.9–1321.4 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1309.7 1302.5–1316.9 | community | LMArena Leaderboard Dataset | |
| Japanese (style control)older version arena=text · category=japanese · style_control=true | 1305.0 1289.7–1320.3 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1304.6 1297.7–1311.5 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1304.3 1298.7–1309.8 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1294.1 1276.7–1311.4 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=vals-ai | high effort | 50.3 % | independent | Vals AI |
| GPQA Diamond | 48.9 % | independent | Epoch AI Benchmarking Hub 2025-01-27 |
reasoning math
| MATH Level 5 | 51.0 % | independent | Epoch AI Benchmarking Hub 2025-01-27 | |
| OTIS Mock AIME 2024–2025 | 6.3 % | independent | Epoch AI Benchmarking Hub 2025-02-25 |
Agent + model results
systems, not bare-model scores
| agent + model Agentless-1.5 + GPT 4o (2024-05-13) | SWE-bench Verified | 38.8 % | unverified | SWE-bench Leaderboard |
| agent + model AutoCodeRover (v20240620) + GPT 4o (2024-05-13) | SWE-bench Verified | 38.4 % | unverified | SWE-bench Leaderboard |
| agent + model AbanteAI MentatBot + GPT 4o (2024-05-13) | SWE-bench Lite | 38.0 % | unverified | SWE-bench Leaderboard |
| agent + model Bytedance MarsCode Agent + GPT 4o (2024-05-13) | SWE-bench Lite | 34.0 % | unverified | SWE-bench Leaderboard |
| agent + model Agentless-1.5 + GPT 4o (2024-05-13) | SWE-bench Lite | 32.0 % | unverified | SWE-bench Leaderboard |
| agent + model CodeShellTester + GPT 4o (2024-05-13) | SWE-bench Lite | 31.3 % | unverified | SWE-bench Leaderboard |
| agent + model AutoCodeRover (v20240620) + GPT 4o (2024-05-13) | SWE-bench Lite | 30.7 % | unverified | SWE-bench Leaderboard |
| agent + model SIMA + GPT 4o (2024-05-13) | SWE-bench Lite | 27.7 % | unverified | SWE-bench Leaderboard |
| agent + model MASAI + GPT 4o (2024-05-13) | SWE-bench Lite | 27.3 % | unverified | SWE-bench Leaderboard |
| agent + model Agentless + GPT 4o (2024-05-13) | SWE-bench Lite | 27.3 % | unverified | SWE-bench Leaderboard |
| agent + model AppMap Navie + GPT 4o (2024-05-13) | SWE-bench Verified | 26.2 % | community | SWE-bench Leaderboard |
| agent + model Moatless Tools + GPT 4o (2024-05-13) | SWE-bench Lite | 24.7 % | community | SWE-bench Leaderboard |
| agent + model SWE-agent + GPT 4o (2024-05-13) | SWE-bench Verified | 23.2 % | community | SWE-bench Leaderboard |
| agent + model AppMap Navie + GPT 4o (2024-05-13) | SWE-bench Lite | 21.7 % | community | SWE-bench Leaderboard |
| agent + model AutoCodeRover (v20240620) + GPT 4o (2024-05-13) | SWE-bench (full test split) | 18.8 % | unverified | SWE-bench Leaderboard |
| agent + model SWE-agent + GPT 4o (2024-05-13) | SWE-bench Lite | 18.3 % | community | SWE-bench Leaderboard |
| agent + model AppMap Navie + GPT 4o (2024-05-13) | SWE-bench (full test split) | 14.6 % | community | SWE-bench Leaderboard |
| agent + model SWE-agent + GPT 4o (2024-05-13) | SWE-bench (full test split) | 12.0 % | community | SWE-bench Leaderboard |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.