Rankings / Anthropic
Claude 3.5 Haiku 20241022
released 2024-10-22
BenchAtlas Index
as of 2026-07-14
Benchmark evidence
42 results
external indices
| ECI | 127.5 points | independent | Epoch AI Benchmarking Hub |
factuality
| SimpleQA Verified | 6.7 % | independent | Epoch AI Benchmarking Hub 2025-11-28 |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1385.1 1379.1–1391.1 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1364.6 1359.6–1369.5 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1357.1 1351.5–1362.8 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1350.9 1341.1–1360.7 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1344.2 1339.6–1348.8 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1344.0 1333.1–1355.0 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1343.2 1337.1–1349.3 | community | LMArena Leaderboard Dataset | |
| French (style control)older version arena=text · category=french · style_control=true | 1342.6 1319.9–1365.3 | 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 | 1341.8 1335.6–1348.1 | community | LMArena Leaderboard Dataset | |
| Polish (style control)older version arena=text · category=polish · style_control=true | 1337.5 1324.3–1350.6 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1336.4 1332.4–1340.4 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1326.3 1320.0–1332.5 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1323.7 1320.5–1326.9 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1322.0 1300.8–1343.1 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1317.7 1309.9–1325.4 | community | LMArena Leaderboard Dataset | |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1316.0 1306.2–1325.7 | 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 | 1315.8 1308.9–1322.6 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1314.6 1309.9–1319.2 | community | LMArena Leaderboard Dataset | |
| German (style control)older version arena=text · category=german · style_control=true | 1314.4 1299.0–1329.8 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1312.8 1302.2–1323.3 | 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 | 1312.6 1307.5–1317.8 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1304.6 1298.2–1311.0 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1304.4 1300.3–1308.6 | 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 | 1304.0 1298.3–1309.8 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1299.4 1291.5–1307.2 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1286.4 1278.9–1293.9 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1269.4 1264.7–1274.1 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1268.2 1249.4–1286.9 | community | LMArena Leaderboard Dataset | |
| Japanese (style control)older version arena=text · category=japanese · style_control=true | 1241.5 1224.8–1258.2 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond | 38.1 % | independent | Epoch AI Benchmarking Hub 2025-03-12 | |
| GPQA Diamond implementation=vals-ai | 37.9 % | independent | Vals AI | |
| MMLU-Pro implementation=vals-ai | 64.1 % | independent | Vals AI |
professional
| CorpFin | 50.8 % | independent | Vals AI | |
| LegalBench | 70.3 % | independent | Vals AI | |
| TaxEval | 57.4 % | independent | Vals AI |
reasoning math
| AIME implementation=vals-ai | 3.3 % | independent | Vals AI | |
| FrontierMath | 0.3 % | independent | Epoch AI Benchmarking Hub 2025-03-07 | |
| MATH-500 implementation=vals-ai | 64.2 % | independent | Vals AI | |
| MATH Level 5 | 46.4 % | independent | Epoch AI Benchmarking Hub 2025-03-12 | |
| OTIS Mock AIME 2024–2025 | 4.3 % | independent | Epoch AI Benchmarking Hub 2025-02-25 |
