BenchAtlas

Rankings / xAI

Grok 4.20 Beta 0309 Reasoning

proprietary

released 2026-03-05

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

30 results
human preference
Coding (style control)older version
arena=text · category=coding · style_control=true
1510.3
1504.41516.3
communityLMArena Leaderboard Dataset
French (style control)older version
arena=text · category=french · style_control=true
1503.1
1488.11518.1
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1502.7
1497.51507.9
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1501.5
1490.81512.3
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1490.3
1484.71496.0
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1488.0
1483.51492.6
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1487.2
1477.51496.9
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
1486.8
1479.91493.6
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1481.4
1473.41489.4
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1479.9
1473.21486.6
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1479.7
1474.81484.7
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1478.2
1468.91487.5
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1477.7
1472.81482.6
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1476.0
1467.51484.5
communityLMArena Leaderboard Dataset
Polish (style control)older version
arena=text · category=polish · style_control=true
1472.1
1455.01489.3
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1471.7
1467.91475.5
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1467.5
1456.71478.2
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
1466.3
1459.91472.7
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1465.7
1460.31471.0
communityLMArena Leaderboard Dataset
Spanish (style control)older version
arena=text · category=spanish · style_control=true
1462.6
1448.11477.1
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1461.8
1457.11466.4
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1459.5
1448.51470.5
communityLMArena Leaderboard Dataset
German (style control)older version
arena=text · category=german · style_control=true
1456.1
1436.61475.5
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
1450.7
1444.71456.8
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
1448.1
1441.71454.5
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1446.8
1439.81453.8
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1445.7
1440.31451.2
communityLMArena Leaderboard Dataset
Korean (style control)older version
arena=text · category=korean · style_control=true
1433.7
1413.41453.9
communityLMArena Leaderboard Dataset
Japanese (style control)older version
arena=text · category=japanese · style_control=true
1423.1
1398.51447.6
communityLMArena Leaderboard Dataset
reasoning math
ARC-AGI-3older version
split=semi_private · model_type=CoT
0.1 %independentARC Prize Leaderboard