ModelsIndexCompareBest forBenchmarksStatusPricingAPI

Grok 4

xAI·Operational·Released 2025-07-09textvision
Context256k
Max output-
Input / 1M-
Output / 1M-
Cached in-
Benchmarks17

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

Chess Puzzles (Epoch AI run)#36/9228% ↗
GPQA Diamond (Epoch AI run)#52/10287% ↗
OTIS Mock AIME 2024-2025 (Epoch AI run)#69/10384% ↗
SAGE (Vals AI)#75/7725.1% ↗
SimpleBench (SimpleBench)#34/7360.5% ↗
WeirdML (Håvard Tveit Ihle)#55/9245.7% ↗
LMArena Elo#97/1411410.8 ↗
LMArena Vision (LMArena)#69/771184.2 ↗
BALROG (BALROG)#9/1943.6% ↗
AIME 2025 (no tools)#7/991.7% ↗
ARC-AGI-2#4/615.9% ↗
GPQA (no tools)#1/487.5% ↗
HMMT 2025 (no tools)#2/290% ↗
Humanity's Last Exam (no tools)#19/3425.4% ↗
Humanity's Last Exam (with tools)#15/1838.6% ↗
LiveCodeBench (Jan - May)79% ↗
USAMO 2025 (no tools)37.5% ↗

Compare

vs Gemini 4 Argonvs GPT-6.1 Solvs Claude Sonnet 5.5vs Muse Spark 1.3vs GPT-6 Solvs GPT-6 Lunavs Claude Opus 5.5vs GPT-6 Astra

More from xAI

Grok 4.7Grok 4.6Grok 4.3Grok 4.5Grok 4 Fast ReasoningGrok 4.20 Reasoning

Grok 4 FAQ

What is Grok 4?
Grok 4 is a large language model from xAI, released on July 9, 2025. It accepts text and image input.
When was Grok 4 released?
xAI released Grok 4 on July 9, 2025.
What is Grok 4's context window?
Grok 4 has a 256K-token context window.
How does Grok 4 score on benchmarks?
Grok 4 has 17 cited benchmark scores, including Chess Puzzles (Epoch AI run) 28%, GPQA Diamond (Epoch AI run) 87% and OTIS Mock AIME 2024-2025 (Epoch AI run) 84%. Each score links to its source.

Access Grok 4 and every other model through one endpoint with automatic failover: Respan gateway.