Rankings / Anthropic
Claude 3 Opus 20240229
released 2024-02-29
BenchAtlas Index
as of 2026-09-11
Benchmark evidence
33 results
external indices
| ECI | 126.9 points | independent | Epoch AI Benchmarking Hub |
factuality
| SimpleQA Verified | 12.6 % | independent | Epoch AI Benchmarking Hub 2026-08-31 |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1354.8 1348.8–1360.7 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1348.1 1338.6–1357.6 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1340.6 1335.5–1345.6 | 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 | 1339.2 1333.0–1345.4 | community | LMArena Leaderboard Dataset | |
| French (style control)older version arena=text · category=french · style_control=true | 1339.2 1320.1–1358.2 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1334.2 1324.2–1344.2 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1333.4 1326.4–1340.4 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1329.0 1322.6–1335.5 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1328.6 1323.7–1333.5 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1326.4 1320.5–1332.2 | community | LMArena Leaderboard Dataset | |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1324.1 1315.9–1332.2 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1324.0 1320.0–1328.1 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1321.8 1315.6–1328.1 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1321.6 1318.5–1324.7 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1318.0 1308.5–1327.5 | community | LMArena Leaderboard Dataset | |
| German (style control)older version arena=text · category=german · style_control=true | 1317.4 1304.7–1330.2 | 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 | 1315.3 1310.0–1320.6 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1314.7 1310.5–1318.9 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1313.8 1309.3–1318.3 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1312.0 1305.4–1318.5 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1310.3 1303.5–1317.1 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1306.0 1286.7–1325.3 | 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 | 1304.9 1297.9–1311.9 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1287.2 1280.7–1293.8 | 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 | 1283.8 1277.6–1289.9 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1269.7 1252.6–1286.7 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1261.4 1256.6–1266.2 | community | LMArena Leaderboard Dataset | |
| Japanese (style control)older version arena=text · category=japanese · style_control=true | 1260.8 1246.4–1275.2 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond | 47.2 % | independent | Epoch AI Benchmarking Hub 2025-01-27 |
reasoning math
| MATH Level 5 | 37.5 % | independent | Epoch AI Benchmarking Hub 2025-01-27 | |
| OTIS Mock AIME 2024–2025 | 4.7 % | independent | Epoch AI Benchmarking Hub 2025-02-25 |
Agent + model results
systems, not bare-model scores
| agent + model SWE-agent + Claude 3 Opus 20240229 | SWE-bench Verified | 15.8 % | community | SWE-bench Leaderboard |
| agent + model SWE-agent + Claude 3 Opus 20240229 | SWE-bench (full test split) | 10.5 % | community | SWE-bench Leaderboard |
| agent + model RAG + Claude 3 Opus 20240229 | SWE-bench Verified | 7.0 % | community | SWE-bench Leaderboard |
| agent + model RAG + Claude 3 Opus 20240229 | SWE-bench Lite | 4.3 % | community | SWE-bench Leaderboard |
| agent + model RAG + Claude 3 Opus 20240229 | SWE-bench (full test split) | 3.8 % | community | SWE-bench Leaderboard |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.
