BenchAtlas

Rankings / Google

Gemini 3 Pro

proprietary

release date unknown

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

28 results
human preference
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1522.5
1511.61533.4
communityLMArena Leaderboard Dataset
German (style control)older version
arena=text · category=german · style_control=true
1521.6
1499.41543.8
communityLMArena Leaderboard Dataset
Coding (style control)older version
arena=text · category=coding · style_control=true
1518.2
1511.11525.3
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1509.9
1504.01515.8
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1508.7
1496.61520.8
communityLMArena Leaderboard Dataset
French (style control)older version
arena=text · category=french · style_control=true
1506.9
1486.91527.0
communityLMArena Leaderboard Dataset
Polish (style control)older version
arena=text · category=polish · style_control=true
1505.1
1488.31521.9
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1503.6
1498.61508.6
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1501.4
1490.21512.5
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1501.3
1495.81506.8
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1501.3
1489.61512.9
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1501.2
1492.31510.0
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1500.3
1493.51507.2
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
1497.3
1489.51505.2
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1495.4
1487.51503.3
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1491.3
1484.71497.8
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1487.5
1482.01492.9
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1485.6
1481.71489.4
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1483.1
1474.81491.4
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
1481.8
1474.71488.8
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1481.1
1467.81494.5
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1477.5
1472.71482.3
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1477.2
1465.71488.6
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
1474.8
1467.41482.2
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1473.1
1466.71479.5
communityLMArena Leaderboard Dataset
Spanish (style control)older version
arena=text · category=spanish · style_control=true
1471.5
1453.61489.3
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
1467.7
1460.21475.3
communityLMArena Leaderboard Dataset
Korean (style control)older version
arena=text · category=korean · style_control=true
1449.7
1426.31473.0
communityLMArena Leaderboard Dataset

Agent + model results

systems, not bare-model scores
agent + model mini-SWE-agent + Gemini 3 ProSWE-bench Multilingual68.7 %communitySWE-bench Leaderboard
agent + model mini-SWE-agent + Gemini 3 ProSWE-bench Multilingual1.0 usd_per_taskcommunitySWE-bench Leaderboard

These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.