BenchAtlas

Rankings / Anthropic

Claude 3 Haiku 20240307

released 2024-03-07

BenchAtlas Index

as of 2026-09-11
Not enough benchmark coverage for a composite score (needs ≥4 families across ≥3 categories). The per-benchmark evidence below stands on its own — sparse coverage is an evidence gap, not a low score.

Benchmark evidence

32 results
external indices
ECI118.3 pointsindependentEpoch AI Benchmarking Hub
human preference
Coding (style control)older version
arena=text · category=coding · style_control=true
1300.9
1294.0–1307.8
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1285.8
1274.9–1296.7
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1285.0
1279.0–1291.0
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1279.4
1268.1–1290.6
communityLMArena Leaderboard Dataset
French (style control)older version
arena=text · category=french · style_control=true
1276.7
1255.8–1297.7
communityLMArena 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
1272.5
1265.3–1279.8
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1270.3
1265.5–1275.2
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1269.2
1262.4–1275.9
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1266.7
1258.4–1274.9
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1266.7
1258.9–1274.4
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1264.8
1259.1–1270.5
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1261.1
1257.3–1264.8
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1252.8
1241.8–1263.7
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1248.8
1239.7–1257.9
communityLMArena 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
1247.7
1239.5–1255.9
communityLMArena Leaderboard Dataset
German (style control)older version
arena=text · category=german · style_control=true
1246.2
1232.0–1260.4
communityLMArena Leaderboard Dataset
Industry Writing And Literature And Language (style control)older version
arena=text · category=industry_writing_and_literature_and_language · style_control=true
1245.9
1239.6–1252.2
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1245.8
1240.8–1250.9
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1244.7
1239.4–1250.1
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1244.6
1237.2–1251.9
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1238.7
1230.9–1246.5
communityLMArena Leaderboard Dataset
Spanish (style control)older version
arena=text · category=spanish · style_control=true
1238.6
1217.7–1259.5
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1231.4
1223.9–1238.9
communityLMArena Leaderboard Dataset
Industry Entertainment And Sports And Media (style control)older version
arena=text · category=industry_entertainment_and_sports_and_media · style_control=true
1220.1
1212.8–1227.4
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1214.8
1207.2–1222.5
communityLMArena Leaderboard Dataset
Korean (style control)older version
arena=text · category=korean · style_control=true
1208.9
1190.0–1227.8
communityLMArena Leaderboard Dataset
Japanese (style control)older version
arena=text · category=japanese · style_control=true
1171.6
1154.7–1188.5
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1170.5
1164.6–1176.4
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond36.3 %independentEpoch AI Benchmarking Hub
2025-01-27
reasoning math
MATH Level 514.9 %independentEpoch AI Benchmarking Hub
2025-01-27
OTIS Mock AIME 2024–20251.8 %independentEpoch AI Benchmarking Hub
2025-02-25

Agent + model results

systems, not bare-model scores
agent + model Tools + Claude 3 Haiku 20240307SWE-bench Verified40.6 %unverifiedSWE-bench Leaderboard

These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.

Related variants

Claude 3 Haiku