BenchAtlas

Rankings / xAI

Grok 3 Mini Beta

released 2025-04-09

BenchAtlas Index

as of 2026-07-14
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

38 results
external indices
ECImedium effort141.0 pointsindependentEpoch AI Benchmarking Hub
ECIlow effort141.0 pointsindependentEpoch AI Benchmarking Hub
ECIhigh effort141.0 pointsindependentEpoch AI Benchmarking Hub
factuality
SimpleQA Verifiedhigh effort21.1 %independentEpoch AI Benchmarking Hub
2025-12-09
human preference
Coding (style control)older version
arena=text · category=coding · style_control=true
1386.5
1377.41395.5
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1381.7
1373.41390.0
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1379.1
1371.91386.4
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1374.9
1356.71393.2
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1374.5
1357.31391.7
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
1371.0
1361.31380.7
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1369.9
1363.41376.5
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1369.5
1355.21383.7
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1369.3
1363.11375.6
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1366.2
1357.01375.5
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1361.6
1346.81376.4
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1361.2
1345.21377.3
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1357.0
1341.61372.3
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1356.7
1351.71361.8
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1353.0
1345.01361.1
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1349.0
1333.61364.4
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
1345.1
1335.11355.2
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1343.1
1333.51352.7
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
1341.5
1332.71350.2
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1340.6
1334.31346.9
communityLMArena Leaderboard Dataset
Polish (style control)older version
arena=text · category=polish · style_control=true
1334.8
1320.51349.2
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1334.6
1323.31345.8
communityLMArena Leaderboard Dataset
Japanese (style control)older version
arena=text · category=japanese · style_control=true
1329.7
1304.81354.5
communityLMArena Leaderboard Dataset
German (style control)older version
arena=text · category=german · style_control=true
1329.2
1303.91354.4
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
1321.3
1311.71330.9
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1319.9
1313.01326.8
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamondlow effort76.3 %independentEpoch AI Benchmarking Hub
2025-04-10
GPQA Diamondhigh effort74.6 %independentEpoch AI Benchmarking Hub
2025-05-26
reasoning math
FrontierMathhigh effort5.9 %independentEpoch AI Benchmarking Hub
2025-04-10
FrontierMathlow effort2.8 %independentEpoch AI Benchmarking Hub
2025-04-10
MATH Level 5low effort90.9 %independentEpoch AI Benchmarking Hub
2025-04-10
MATH Level 5high effort88.1 %independentEpoch AI Benchmarking Hub
2025-04-10
OTIS Mock AIME 2024–2025high effort77.8 %independentEpoch AI Benchmarking Hub
2025-04-10
OTIS Mock AIME 2024–2025low effort62.2 %independentEpoch AI Benchmarking Hub
2025-04-10