Rankings / Google
Gemma 3 4B IT
open weightsrelease date unknown
BenchAtlas Index
as of 2026-09-11
Benchmark evidence
17 results
external indices
| ECI | 116.0 points | independent | Epoch AI Benchmarking Hub |
human preference
| Industry Life And Physical And Social Science (style control)older version arena=text · category=industry_life_and_physical_and_social_science · style_control=true | 1315.3 1294.5–1336.1 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1309.3 1297.7–1321.0 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1303.1 1293.8–1312.4 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1300.6 1282.0–1319.2 | community | LMArena Leaderboard Dataset | |
| Industry Writing And Literature And Language (style control)older version arena=text · category=industry_writing_and_literature_and_language · style_control=true | 1297.5 1280.3–1314.6 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1291.1 1277.0–1305.1 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1284.8 1264.3–1305.2 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1283.8 1266.5–1301.1 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1274.6 1252.3–1296.9 | community | LMArena Leaderboard Dataset | |
| Coding (style control)older version arena=text · category=coding · style_control=true | 1273.9 1250.3–1297.6 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1272.2 1248.6–1295.8 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1267.3 1251.0–1283.6 | community | LMArena Leaderboard Dataset | |
| Industry Entertainment And Sports And Media (style control)older version arena=text · category=industry_entertainment_and_sports_and_media · style_control=true | 1247.8 1227.1–1268.4 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1234.5 1220.4–1248.5 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond | 23.2 % | independent | Epoch AI Benchmarking Hub 2026-08-28 |
reasoning math
| OTIS Mock AIME 2024–2025 | 7.5 % | independent | Epoch AI Benchmarking Hub 2026-08-28 |
