Rankings / xAI
Grok 4 0709
released 2025-07-09
BenchAtlas Index
as of 2026-09-11
base configuration
rank #189
10 families · 5 categories · high
base configuration
rank #221
5 families · 3 categories · medium
Benchmark evidence
54 results
external indices
| ECI | 146.5 points | independent | Epoch AI Benchmarking Hub | |
| ECI | high effort | 146.5 points | independent | Epoch AI Benchmarking Hub |
factuality
| SimpleQA Verified | 47.9 % | independent | Epoch AI Benchmarking Hub 2025-12-08 |
human preference
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1437.9 1424.9–1450.9 | community | LMArena Leaderboard Dataset | |
| Coding (style control)older version arena=text · category=coding · style_control=true | 1435.0 1428.1–1442.0 | 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 | 1434.1 1426.5–1441.8 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1432.9 1420.0–1445.9 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1431.6 1418.2–1445.0 | community | LMArena Leaderboard Dataset | |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1429.6 1418.1–1441.1 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1426.5 1414.1–1438.9 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1425.2 1419.5–1430.9 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1423.2 1416.4–1430.0 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1423.0 1411.1–1434.8 | community | LMArena Leaderboard Dataset | |
| French (style control)older version arena=text · category=french · style_control=true | 1422.8 1397.4–1448.2 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1420.2 1415.2–1425.3 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1419.1 1413.9–1424.3 | community | LMArena Leaderboard Dataset | |
| Polish (style control)older version arena=text · category=polish · style_control=true | 1418.9 1407.0–1430.9 | community | LMArena Leaderboard Dataset | |
| German (style control)older version arena=text · category=german · style_control=true | 1417.9 1397.6–1438.1 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1415.6 1408.9–1422.3 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1413.8 1394.4–1433.1 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1412.1 1404.3–1419.9 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1411.0 1407.0–1414.9 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1410.2 1399.1–1421.2 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1400.8 1395.9–1405.6 | 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 | 1398.3 1391.6–1405.1 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1396.7 1391.3–1402.1 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1396.6 1390.4–1402.8 | 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 | 1394.7 1387.3–1402.1 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1394.5 1385.9–1403.0 | community | LMArena Leaderboard Dataset | |
| Japanese (style control)older version arena=text · category=japanese · style_control=true | 1394.4 1373.8–1414.9 | 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 | 1386.3 1379.0–1393.6 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1369.9 1348.2–1391.5 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=vals-ai | 88.1 % | independent | Vals AI | |
| GPQA Diamond | 87.0 % | independent | Epoch AI Benchmarking Hub | |
| MMLU-Pro implementation=vals-ai | 85.3 % | independent | Vals AI |
multimodal
| MMMU implementation=vals-ai | 76.3 % | independent | Vals AI |
professional
| CaseLaw | 65.8 % | independent | Vals AI | |
| CorpFin | 66.0 % | independent | Vals AI | |
| LegalBench | 83.2 % | independent | Vals AI | |
| MedQA | 92.5 % | independent | Vals AI | |
| TaxEval | 65.1 % | independent | Vals AI |
reasoning math
| AIME implementation=vals-ai | 90.6 % | independent | Vals AI | |
| ARC-AGI-1older version split=public_eval · model_type=CoT | 73.7 % | independent | ARC Prize Leaderboard | |
| ARC-AGI-1older version split=semi_private · model_type=CoT | 66.7 % | independent | ARC Prize Leaderboard | |
| ARC-AGI-2 split=public_eval · model_type=CoT | 21.1 % | independent | ARC Prize Leaderboard | |
| ARC-AGI-2 split=semi_private · model_type=CoT | 16.0 % | independent | ARC Prize Leaderboard | |
| ARC-AGI-2 split=semi_private · model_type=CoT | 2.2 usd_per_task | independent | ARC Prize Leaderboard | |
| ARC-AGI-2 split=public_eval · model_type=CoT | 2.1 usd_per_task | independent | ARC Prize Leaderboard | |
| ARC-AGI-1older version split=semi_private · model_type=CoT | 1.0 usd_per_task | independent | ARC Prize Leaderboard | |
| ARC-AGI-1older version split=public_eval · model_type=CoT | 0.8 usd_per_task | independent | ARC Prize Leaderboard | |
| FrontierMath | 19.7 % | independent | Epoch AI Benchmarking Hub 2025-11-13 | |
| FrontierMath Tier 4older version | 2.1 % | independent | Epoch AI Benchmarking Hub 2025-08-11 | |
| MATH-500 implementation=vals-ai | 96.2 % | independent | Vals AI | |
| OTIS Mock AIME 2024–2025 | 84.0 % | independent | Epoch AI Benchmarking Hub |
Agent + model results
systems, not bare-model scores
| agent + model OpenHands + Grok 4 0709 | Terminal-Bench 2.0 | 27.2 % | community | Terminal-Bench Leaderboard |
| agent + model mini-SWE-agent + Grok 4 0709 | Terminal-Bench 2.0 | 25.4 % | community | Terminal-Bench Leaderboard |
| agent + model terminus-2 + Grok 4 0709 | Terminal-Bench 2.0 | 23.1 % | community | Terminal-Bench Leaderboard |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.