Rankings / xAI
Grok 4 Fast Reasoning
released 2025-10-21
BenchAtlas Index
as of 2026-07-14
base configuration
rank #158
8 families · 3 categories · medium
Benchmark evidence
42 results
human preference
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1442.8 1420.1–1465.5 | community | LMArena Leaderboard Dataset | |
| Coding (style control)older version arena=text · category=coding · style_control=true | 1437.1 1427.7–1446.5 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1435.2 1415.2–1455.1 | 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 | 1432.7 1421.9–1443.4 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1425.7 1408.8–1442.7 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1425.6 1418.2–1433.1 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1423.6 1415.2–1432.0 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1417.8 1397.9–1437.6 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1414.0 1407.4–1420.5 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1412.9 1386.9–1439.0 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1412.7 1406.2–1419.1 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1411.8 1393.0–1430.6 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1411.4 1402.4–1420.4 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1411.0 1393.2–1428.7 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1406.3 1395.6–1417.0 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1404.0 1399.0–1409.1 | 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 | 1400.7 1390.9–1410.6 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1399.5 1382.0–1416.9 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1390.4 1383.9–1396.9 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1388.3 1380.0–1396.6 | 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 | 1388.1 1378.9–1397.3 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1387.2 1380.2–1394.2 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1381.3 1369.4–1393.1 | community | LMArena Leaderboard Dataset | |
| Polish (style control)older version arena=text · category=polish · style_control=true | 1380.5 1358.8–1402.2 | 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 | 1367.8 1357.6–1378.0 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=vals-ai | 85.4 % | independent | Vals AI | |
| MMLU-Pro implementation=vals-ai | 79.7 % | independent | Vals AI |
multimodal
| MMMU implementation=vals-ai | 72.8 % | independent | Vals AI |
professional
| CaseLaw | 65.7 % | independent | Vals AI | |
| CorpFin | 66.9 % | independent | Vals AI | |
| LegalBench | 80.6 % | independent | Vals AI | |
| MedQA | 92.1 % | independent | Vals AI | |
| TaxEval | 75.7 % | independent | Vals AI |
reasoning math
| AIME implementation=vals-ai | 91.3 % | independent | Vals AI | |
| ARC-AGI-1older version split=public_eval · model_type=CoT | 58.1 % | independent | ARC Prize Leaderboard | |
| ARC-AGI-1older version split=semi_private · model_type=CoT | 48.5 % | independent | ARC Prize Leaderboard | |
| ARC-AGI-2 split=semi_private · model_type=CoT | 5.3 % | independent | ARC Prize Leaderboard | |
| ARC-AGI-2 split=public_eval · model_type=CoT | 4.6 % | independent | ARC Prize Leaderboard | |
| ARC-AGI-2 split=public_eval · model_type=CoT | 0.1 usd_per_task | independent | ARC Prize Leaderboard | |
| ARC-AGI-2 split=semi_private · model_type=CoT | 0.1 usd_per_task | independent | ARC Prize Leaderboard | |
| ARC-AGI-1older version split=semi_private · model_type=CoT | 0.0 usd_per_task | independent | ARC Prize Leaderboard | |
| ARC-AGI-1older version split=public_eval · model_type=CoT | 0.0 usd_per_task | independent | ARC Prize Leaderboard |
