Rankings / xAI
Grok 4.5
proprietaryreleased 2026-07-08
BenchAtlas Index
as of 2026-07-14
high effort
rank #25
7 families · 5 categories · medium
high effort
rank #40
7 families · 4 categories · medium
base configuration
rank #119
6 families · 4 categories · medium
Benchmark evidence
42 results
agentic coding
| Release 2026-06-25 tasks_counted=3 · livebench_version=2026-06-25 | 59.8 % | independent | LiveBench | |
| τ²-Bench subset=banking | high effort | 32.6 % | independent | Artificial Analysis |
coding
| Release 2026-06-25 tasks_counted=2 · livebench_version=2026-06-25 | 68.6 % | independent | LiveBench | |
| SciCode | high effort | 54.1 % | independent | Artificial Analysis |
data analysis
| Release 2026-06-25 tasks_counted=3 · livebench_version=2026-06-25 | 73.0 % | independent | LiveBench |
external indices
| AA Coding Index | high effort | 72.4 points | independent | Artificial Analysis |
| Intelligence Index v4.1 | high effort | 53.8 points | independent | Artificial Analysis |
| ECI | high effort | 153.2 points | independent | Epoch AI Benchmarking Hub |
| ECI | 153.2 points | independent | Epoch AI Benchmarking Hub | |
| Vals Index | high effort | 65.3 points | independent | Vals AI |
factuality
| SimpleQA Verified | high effort | 53.5 % | independent | Epoch AI Benchmarking Hub 2026-07-08 |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1522.0 1504.5–1539.5 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1501.2 1486.5–1516.0 | 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 | 1489.6 1465.2–1514.0 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1485.3 1470.8–1499.9 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1483.3 1471.5–1495.2 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1478.1 1459.7–1496.6 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1472.0 1459.3–1484.7 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1471.3 1456.7–1485.8 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1470.9 1448.2–1493.5 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1465.1 1455.5–1474.6 | 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 | 1462.9 1443.9–1481.9 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1457.5 1441.2–1473.9 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1455.1 1442.9–1467.4 | 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 | 1451.7 1429.7–1473.6 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1444.7 1422.0–1467.3 | 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 | 1440.5 1420.9–1460.0 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond | high effort | 93.4 % | independent | Epoch AI Benchmarking Hub 2026-07-08 |
| GPQA Diamond implementation=artificial-analysis | high effort | 93.1 % | independent | Artificial Analysis |
| GPQA Diamond implementation=vals-ai | high effort | 92.9 % | independent | Vals AI |
| Humanity's Last Exam implementation=artificial-analysis | high effort | 40.3 % | independent | Artificial Analysis |
| MMLU-Pro implementation=vals-ai | high effort | 89.2 % | independent | Vals AI |
language
| Release 2026-06-25 tasks_counted=3 · livebench_version=2026-06-25 | 82.8 % | independent | LiveBench |
long context instruction
| AA-LCR | high effort | 67.7 % | independent | Artificial Analysis |
| Release 2026-06-25 tasks_counted=4 · livebench_version=2026-06-25 | 71.5 % | independent | LiveBench |
multimodal
| MMMU implementation=vals-ai | high effort | 61.8 % | independent | Vals AI |
professional
| CorpFin | high effort | 67.4 % | independent | Vals AI |
| LegalBench | high effort | 86.0 % | independent | Vals AI |
| TaxEval | high effort | 71.7 % | independent | Vals AI |
reasoning math
| Release 2026-06-25 tasks_counted=4 · livebench_version=2026-06-25 | 90.8 % | independent | LiveBench | |
| Release 2026-06-25 tasks_counted=4 · livebench_version=2026-06-25 | 87.2 % | independent | LiveBench | |
| OTIS Mock AIME 2024–2025 | high effort | 97.8 % | independent | Epoch AI Benchmarking Hub 2026-07-08 |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + Grok 4.5 | Terminal-Bench 2.1 | 81.7 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.