BenchAtlas

Rankings / Google DeepMind

Gemma 2 9B 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
ECI119.8 pointsindependentEpoch AI Benchmarking Hub
human preference
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1285.0
1273.31296.6
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1280.4
1274.31286.6
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
1279.6
1272.21287.0
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1278.0
1273.21282.8
communityLMArena Leaderboard Dataset
Coding (style control)older version
arena=text · category=coding · style_control=true
1270.3
1263.01277.6
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
1267.9
1261.81273.9
communityLMArena Leaderboard Dataset
Spanish (style control)older version
arena=text · category=spanish · style_control=true
1267.4
1241.51293.4
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1266.6
1262.81270.4
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1265.4
1255.61275.2
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1265.1
1257.21273.0
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1261.4
1254.21268.6
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
1260.5
1251.91269.1
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1259.3
1251.21267.5
communityLMArena Leaderboard Dataset
French (style control)older version
arena=text · category=french · style_control=true
1259.2
1232.61285.7
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1259.0
1246.31271.7
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1258.1
1250.61265.7
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1256.9
1250.91262.8
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1251.1
1243.81258.4
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
1247.6
1240.51254.7
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1246.7
1241.71251.7
communityLMArena Leaderboard Dataset
German (style control)older version
arena=text · category=german · style_control=true
1245.2
1229.11261.4
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1244.7
1239.41250.0
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1238.2
1230.01246.3
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1236.5
1224.51248.4
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1219.7
1212.01227.5
communityLMArena Leaderboard Dataset
Korean (style control)older version
arena=text · category=korean · style_control=true
1202.4
1181.41223.5
communityLMArena Leaderboard Dataset
Japanese (style control)older version
arena=text · category=japanese · style_control=true
1195.1
1177.61212.7
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1172.9
1166.91178.8
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond27.5 %independentEpoch AI Benchmarking Hub
2025-01-27
reasoning math
MATH Level 521.0 %independentEpoch AI Benchmarking Hub
2025-01-27
OTIS Mock AIME 2024–20250.6 %independentEpoch AI Benchmarking Hub
2025-03-07