BenchAtlas

Rankings / cohere

Command A 03 2025

open weights

release date unknown

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

38 results
human preference
Coding (style control)older version
arena=text · category=coding · style_control=true
1389.3
1383.11395.5
communityLMArena Leaderboard Dataset
French (style control)older version
arena=text · category=french · style_control=true
1383.1
1360.91405.2
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1379.9
1374.81385.0
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1377.6
1367.31388.0
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1375.3
1369.31381.4
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1374.9
1363.81386.0
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
1370.2
1363.61376.8
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1369.4
1363.31375.6
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1367.8
1363.11372.4
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1365.7
1361.21370.2
communityLMArena Leaderboard Dataset
Spanish (style control)older version
arena=text · category=spanish · style_control=true
1365.7
1347.91383.4
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1360.9
1354.21367.5
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1358.9
1348.91368.8
communityLMArena Leaderboard Dataset
German (style control)older version
arena=text · category=german · style_control=true
1358.1
1341.81374.4
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1353.6
1350.11357.1
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
1351.1
1344.31357.9
communityLMArena Leaderboard Dataset
Polish (style control)older version
arena=text · category=polish · style_control=true
1350.2
1338.81361.6
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
1347.4
1341.61353.2
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1341.5
1336.21346.8
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1339.8
1328.51351.1
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1339.2
1330.51348.0
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1335.7
1331.31340.0
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1335.3
1328.11342.5
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
1329.2
1322.91335.5
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1325.2
1315.51334.8
communityLMArena Leaderboard Dataset
Korean (style control)older version
arena=text · category=korean · style_control=true
1314.7
1296.21333.2
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1314.0
1309.11319.0
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1309.2
1299.91318.4
communityLMArena Leaderboard Dataset
Japanese (style control)older version
arena=text · category=japanese · style_control=true
1305.5
1287.61323.4
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond
implementation=vals-ai
48.5 %independentVals AI
MMLU-Pro
implementation=vals-ai
69.2 %independentVals AI
professional
CaseLaw64.5 %independentVals AI
CorpFin46.0 %independentVals AI
LegalBench79.7 %independentVals AI
MedQA80.5 %independentVals AI
TaxEval61.4 %independentVals AI
reasoning math
AIME
implementation=vals-ai
13.3 %independentVals AI
MATH-500
implementation=vals-ai
76.2 %independentVals AI