Rankings / Google DeepMind
Gemini 1.5 Flash 002
released 2024-09-24
BenchAtlas Index
as of 2026-09-11
base configuration
rank #411
6 families · 3 categories · medium
base configuration
rank #415
7 families · 4 categories · medium
Benchmark evidence
40 results
external indices
| ECI | 129.4 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 | 1327.1 1318.8–1335.5 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1327.0 1313.5–1340.5 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1326.5 1311.4–1341.6 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1323.0 1314.5–1331.5 | community | LMArena Leaderboard Dataset | |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1321.9 1310.4–1333.4 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1321.3 1314.4–1328.2 | community | LMArena Leaderboard Dataset | |
| Coding (style control)older version arena=text · category=coding · style_control=true | 1316.2 1308.2–1324.3 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1314.5 1309.1–1320.0 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1313.0 1304.7–1321.2 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1309.0 1304.7–1313.2 | 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 | 1308.5 1301.5–1315.5 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1306.9 1298.0–1315.8 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1302.9 1296.2–1309.6 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1302.0 1292.8–1311.3 | community | LMArena 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 | 1297.7 1288.0–1307.4 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1297.5 1288.5–1306.5 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1295.7 1290.0–1301.3 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1289.8 1283.9–1295.7 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1288.7 1280.0–1297.3 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1283.8 1270.6–1296.9 | community | LMArena Leaderboard Dataset | |
| German (style control)older version arena=text · category=german · style_control=true | 1277.9 1256.2–1299.6 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1276.9 1268.6–1285.3 | 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 | 1272.8 1264.6–1281.1 | community | LMArena Leaderboard Dataset | |
| Japanese (style control)older version arena=text · category=japanese · style_control=true | 1257.0 1235.1–1279.0 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1246.3 1239.7–1252.9 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1232.1 1203.3–1260.8 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond | 47.3 % | independent | Epoch AI Benchmarking Hub 2025-01-27 | |
| GPQA Diamond implementation=vals-ai | 46.0 % | independent | Vals AI | |
| MMLU-Pro implementation=vals-ai | 65.6 % | independent | Vals AI |
multimodal
| MMMU implementation=vals-ai | 57.2 % | independent | Vals AI | |
| VISTA | 34.0 % 32.6–35.4 | independent | Scale Labs |
professional
| CorpFin | 38.2 % | independent | Vals AI | |
| LegalBench | 63.2 % | independent | Vals AI | |
| TaxEval | 48.2 % | independent | Vals AI |
reasoning math
| AIME implementation=vals-ai | 17.3 % | independent | Vals AI | |
| FrontierMath | 0.0 % | independent | Epoch AI Benchmarking Hub 2025-03-07 | |
| MATH-500 implementation=vals-ai | 78.8 % | independent | Vals AI | |
| MATH Level 5 | 61.9 % | independent | Epoch AI Benchmarking Hub 2025-01-27 | |
| OTIS Mock AIME 2024–2025 | 16.3 % | independent | Epoch AI Benchmarking Hub 2025-02-25 |
