BenchAtlas

Rankings / Google DeepMind

Gemma 2 27B IT

released 2024-06-24

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
ECI122.0 pointsindependentEpoch AI Benchmarking Hub
human preference
French (style control)older version
arena=text · category=french · style_control=true
1312.0
1288.71335.3
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1311.5
1301.11322.0
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1309.7
1304.21315.2
communityLMArena Leaderboard Dataset
Coding (style control)older version
arena=text · category=coding · style_control=true
1304.5
1298.11310.9
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
1303.8
1297.21310.4
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1300.3
1291.41309.1
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1299.9
1293.01306.8
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1298.9
1294.61303.3
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
1296.9
1291.41302.5
communityLMArena Leaderboard Dataset
Spanish (style control)older version
arena=text · category=spanish · style_control=true
1293.9
1271.11316.6
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1292.2
1285.31299.1
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1290.7
1283.41297.9
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1290.6
1279.31301.9
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1289.1
1285.71292.5
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1288.1
1281.71294.5
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1281.7
1276.51287.0
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1279.7
1273.11286.2
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
1278.0
1270.31285.6
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1274.2
1269.71278.7
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
1272.4
1266.01278.9
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1270.8
1266.01275.6
communityLMArena Leaderboard Dataset
German (style control)older version
arena=text · category=german · style_control=true
1269.0
1254.51283.5
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1264.7
1257.51271.9
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1259.1
1248.51269.7
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1247.1
1240.21254.0
communityLMArena Leaderboard Dataset
Korean (style control)older version
arena=text · category=korean · style_control=true
1237.6
1218.51256.7
communityLMArena Leaderboard Dataset
Japanese (style control)older version
arena=text · category=japanese · style_control=true
1228.8
1213.11244.5
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1210.5
1205.21215.8
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond36.5 %independentEpoch AI Benchmarking Hub
2025-01-27
reasoning math
MATH Level 527.9 %independentEpoch AI Benchmarking Hub
2025-01-27
OTIS Mock AIME 2024–20251.4 %independentEpoch AI Benchmarking Hub
2025-03-07