Rankings / Google DeepMind
Gemini 2.5 Flash Preview 09 2025
released 2025-09-25
BenchAtlas Index
as of 2026-07-14
Benchmark evidence
46 results
external indices
| ECI | 16K budget | 143.1 points | independent | Epoch AI Benchmarking Hub |
| ECI | 143.1 points | independent | Epoch AI Benchmarking Hub |
human preference
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1447.8 1432.1–1463.5 | community | LMArena Leaderboard Dataset | |
| French (style control)older version arena=text · category=french · style_control=true | 1439.6 1412.9–1466.3 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1439.5 1424.8–1454.2 | community | LMArena 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 | 1436.7 1428.3–1445.2 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1428.5 1415.7–1441.2 | community | LMArena Leaderboard Dataset | |
| Coding (style control)older version arena=text · category=coding · style_control=true | 1428.3 1420.8–1435.8 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1428.1 1413.1–1443.1 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1423.0 1416.3–1429.8 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1422.9 1416.8–1429.0 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1420.1 1405.6–1434.6 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1420.0 1414.8–1425.2 | community | LMArena Leaderboard Dataset | |
| German (style control)older version arena=text · category=german · style_control=true | 1419.0 1394.7–1443.3 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1417.4 1410.3–1424.5 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1411.5 1398.4–1424.6 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1411.4 1406.0–1416.8 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1404.4 1400.3–1408.4 | 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 | 1402.6 1394.6–1410.6 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1401.7 1395.0–1408.3 | community | LMArena Leaderboard Dataset | |
| Polish (style control)older version arena=text · category=polish · style_control=true | 1400.6 1383.4–1417.8 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1400.1 1392.0–1408.2 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1399.6 1387.5–1411.7 | 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 | 1394.8 1387.4–1402.3 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1393.9 1388.7–1399.2 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1387.2 1365.7–1408.8 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1386.5 1380.8–1392.1 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1382.8 1373.6–1392.0 | 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 | 1380.9 1372.9–1388.9 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1377.9 1354.0–1401.8 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=vals-ai | 81.6 % | independent | Vals AI | |
| GPQA Diamond implementation=vals-ai | thinking | 76.5 % | independent | Vals AI |
| MMLU-Pro implementation=vals-ai | 83.7 % | independent | Vals AI | |
| MMLU-Pro implementation=vals-ai | thinking | 83.7 % | independent | Vals AI |
multimodal
| MMMU implementation=vals-ai | thinking | 80.8 % | independent | Vals AI |
| MMMU implementation=vals-ai | 79.5 % | independent | Vals AI |
professional
| CorpFin | thinking | 59.8 % | independent | Vals AI |
| CorpFin | 59.0 % | independent | Vals AI | |
| LegalBench | thinking | 82.6 % | independent | Vals AI |
| LegalBench | 82.5 % | independent | Vals AI | |
| MedQA | 91.4 % | independent | Vals AI | |
| MedQA | thinking | 91.2 % | independent | Vals AI |
| TaxEval | 72.7 % | independent | Vals AI | |
| TaxEval | thinking | 72.4 % | independent | Vals AI |
reasoning math
| AIME implementation=vals-ai | thinking | 51.5 % | independent | Vals AI |
| AIME implementation=vals-ai | 49.8 % | independent | Vals AI |
