Rankings / Google
Gemini 3 Flash
proprietaryrelease date unknown
BenchAtlas Index
as of 2026-07-14
Benchmark evidence
57 results
human preference
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1521.4 1506.0–1536.7 | community | LMArena Leaderboard Dataset | |
| Coding (style control)older version arena=text · category=coding · style_control=true | 1508.5 1500.5–1516.4 | community | LMArena Leaderboard Dataset | |
| French (style control)older version arena=text · category=french · style_control=true | 1505.2 1482.2–1528.1 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1500.8 1494.2–1507.4 | community | LMArena Leaderboard Dataset | |
| Polish (style control)older version arena=text · category=polish · style_control=true | 1497.0 1477.0–1517.1 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1496.9 1483.6–1510.2 | community | LMArena Leaderboard Dataset | |
| German (style control)older version arena=text · category=german · style_control=true | 1495.1 1468.7–1521.4 | community | LMArena Leaderboard Dataset | |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | minimal effort | 1494.8 1484.2–1505.3 | community | LMArena Leaderboard Dataset |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1492.4 1486.8–1498.0 | community | LMArena Leaderboard Dataset | |
| Coding (style control)older version arena=text · category=coding · style_control=true | minimal effort | 1492.0 1486.7–1497.2 | community | LMArena Leaderboard Dataset |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1487.6 1480.2–1494.9 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1487.0 1474.5–1499.6 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | minimal effort | 1486.9 1482.3–1491.5 | community | LMArena Leaderboard Dataset |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1486.0 1475.6–1496.5 | 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 | 1486.0 1477.2–1494.9 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1485.4 1479.1–1491.7 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1485.3 1472.1–1498.6 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1483.4 1474.8–1492.1 | 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 | minimal effort | 1481.5 1475.5–1487.5 | community | LMArena Leaderboard Dataset |
| French (style control)older version arena=text · category=french · style_control=true | minimal effort | 1479.3 1464.8–1493.9 | community | LMArena Leaderboard Dataset |
| Polish (style control)older version arena=text · category=polish · style_control=true | minimal effort | 1479.1 1464.7–1493.5 | community | LMArena Leaderboard Dataset |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | minimal effort | 1478.1 1469.5–1486.7 | community | LMArena Leaderboard Dataset |
| German (style control)older version arena=text · category=german · style_control=true | minimal effort | 1477.8 1459.8–1495.9 | community | LMArena Leaderboard Dataset |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | minimal effort | 1477.0 1471.1–1483.0 | community | LMArena Leaderboard Dataset |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | minimal effort | 1476.0 1472.0–1480.0 | community | LMArena Leaderboard Dataset |
| Math (style control)older version arena=text · category=math · style_control=true | 1475.9 1462.8–1489.0 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1475.5 1468.2–1482.9 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1474.9 1468.8–1480.9 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1473.2 1468.8–1477.6 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | minimal effort | 1473.0 1468.0–1477.9 | community | LMArena Leaderboard Dataset |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1472.3 1456.7–1487.9 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | minimal effort | 1471.3 1463.2–1479.5 | community | LMArena Leaderboard Dataset |
| Russian (style control)older version arena=text · category=russian · style_control=true | minimal effort | 1470.2 1463.0–1477.4 | 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 | 1470.0 1461.7–1478.3 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1469.7 1448.8–1490.7 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1467.4 1461.7–1473.0 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | minimal effort | 1465.8 1457.8–1473.8 | community | LMArena Leaderboard Dataset |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | minimal effort | 1464.6 1460.2–1469.0 | community | LMArena Leaderboard Dataset |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | minimal effort | 1463.1 1458.2–1468.0 | community | LMArena Leaderboard Dataset |
| English (style control)older version arena=text · category=english · style_control=true | minimal effort | 1462.3 1458.1–1466.5 | 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 | 1460.9 1453.0–1468.9 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | minimal effort | 1459.6 1456.4–1462.8 | community | LMArena Leaderboard Dataset |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1458.4 1451.1–1465.6 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1458.3 1448.8–1467.8 | 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 | minimal effort | 1455.6 1450.0–1461.3 | community | LMArena Leaderboard Dataset |
| Math (style control)older version arena=text · category=math · style_control=true | minimal effort | 1454.0 1444.8–1463.3 | 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 | 1453.3 1444.7–1461.8 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | minimal effort | 1452.3 1448.2–1456.4 | community | LMArena Leaderboard Dataset |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | minimal effort | 1450.1 1440.0–1460.2 | 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 | minimal effort | 1448.7 1443.3–1454.1 | community | LMArena Leaderboard Dataset |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | minimal effort | 1447.9 1441.7–1454.2 | community | LMArena Leaderboard Dataset |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1447.0 1420.8–1473.3 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | minimal effort | 1445.1 1430.9–1459.3 | community | LMArena Leaderboard Dataset |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | minimal effort | 1444.1 1439.2–1449.0 | 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 | minimal effort | 1440.7 1435.0–1446.4 | community | LMArena Leaderboard Dataset |
| Japanese (style control)older version arena=text · category=japanese · style_control=true | minimal effort | 1439.7 1414.9–1464.6 | community | LMArena Leaderboard Dataset |
| Korean (style control)older version arena=text · category=korean · style_control=true | minimal effort | 1433.1 1414.4–1451.9 | community | LMArena Leaderboard Dataset |
Agent + model results
systems, not bare-model scores
| agent + model mini-SWE-agent + Gemini 3 Flash | SWE-bench Multilingual | 72.7 % | community | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + Gemini 3 Flash | SWE-bench Multilingual | 0.4 usd_per_task | community | SWE-bench Leaderboard |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.
