BenchAtlas

Rankings / Google DeepMind

Gemma 3 27B IT

released 2025-03-12

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

37 results
external indices
ECI130.0 pointsindependentEpoch AI Benchmarking Hub
human preference
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1405.1
1392.41417.8
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
1391.1
1384.01398.3
communityLMArena Leaderboard Dataset
French (style control)older version
arena=text · category=french · style_control=true
1386.0
1362.11410.0
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1382.6
1371.01394.3
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
1376.6
1368.91384.3
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1376.3
1370.71382.0
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1376.3
1371.51381.0
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1375.0
1368.31381.7
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1370.9
1359.51382.3
communityLMArena Leaderboard Dataset
Polish (style control)older version
arena=text · category=polish · style_control=true
1369.2
1357.11381.3
communityLMArena Leaderboard Dataset
German (style control)older version
arena=text · category=german · style_control=true
1368.8
1351.41386.3
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1366.5
1356.71376.3
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1365.9
1360.71371.1
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1365.1
1361.41368.8
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1364.1
1356.61371.6
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1358.3
1350.81365.9
communityLMArena Leaderboard Dataset
Coding (style control)older version
arena=text · category=coding · style_control=true
1357.9
1350.91364.9
communityLMArena Leaderboard Dataset
Spanish (style control)older version
arena=text · category=spanish · style_control=true
1357.2
1336.81377.6
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
1354.3
1348.11360.5
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1349.4
1344.71354.1
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1348.3
1340.61356.1
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1343.4
1337.61349.1
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1339.8
1329.61350.0
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1335.7
1322.81348.6
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1330.9
1325.61336.1
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
1327.1
1320.11334.0
communityLMArena Leaderboard Dataset
Korean (style control)older version
arena=text · category=korean · style_control=true
1323.0
1302.21343.9
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1322.1
1312.51331.6
communityLMArena Leaderboard Dataset
Japanese (style control)older version
arena=text · category=japanese · style_control=true
1308.9
1289.91327.8
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond48.9 %independentEpoch AI Benchmarking Hub
2025-03-13
GPQA Diamond47.7 %independentEpoch AI Benchmarking Hub
2026-08-27
GPQA Diamond43.9 %independentEpoch AI Benchmarking Hub
2026-08-06
reasoning math
MATH Level 574.0 %independentEpoch AI Benchmarking Hub
2025-03-13
OTIS Mock AIME 2024–202522.5 %independentEpoch AI Benchmarking Hub
2026-08-27
OTIS Mock AIME 2024–202522.2 %independentEpoch AI Benchmarking Hub
2026-08-06
OTIS Mock AIME 2024–202519.7 %independentEpoch AI Benchmarking Hub
2025-03-13