Grok 4.6 (high)
SpaceXAIGrokProprietary
Description
Grok 4.6 is SpaceXAI's frontier model built for coding, agentic tasks, and knowledge work. It builds on Grok 4.5 with a particular focus on long-running agents and more ambitious interactive and visual work. The model supports text and image inputs, reasoning, function calling, structured outputs, and a 500K-token context window.
Release Date
2026-08-12
Parameters
—
Context Length
500K
Modalities
image, pdf, text
Capability Radar
44
general
74
coding
95
reasoning
71
science
20
agents
80
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 27 | 93.0 | AA |
| General Ranking | 35 | 76.0 | AA |
| Science | 37 | 83.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Agents
AA-Briefcase
1577.00 / 3000SR
Code
CursorBench v3.2
69.9%SR
DeepSWE 1.1
65.9%SR
APEX-SWE
56.4%SR
General
GDPval-AA
1753.00 / 3000SR
AA-Index
61.0%SR
Knowledge
Harvey LAB (Vals)
15.8%SR
Reasoning
FrontierCode
61.3%SR
APEX-Agents
57.5%SR
Terminal-Bench 3.0
26.0%SR
Terminal-Bench 4.0
20.3%
AA Evaluation Indices
(Artificial Analysis)Gpqa(NYU + Cohere + Anthropic (2023))94.9
Terminalbench V2 188.4
Lcr(Artificial Analysis)80.3
Coding Index(Artificial Analysis)76.8
Scicode(UIUC + Argonne National Lab (2024))56.5
Tau Banking50.7
Intelligence Index(Artificial Analysis)44.3
Hle(Center for AI Safety + Scale AI (2025))42.9
LLM Stats Category Scores
(LLM Stats (zeroeval))Legal100
Finance100
Productivity100
Reasoning100
Agents100
General100
Code40
Tool Calling20
Pricing
Input Price$2 / 1M tokens
Output Price$6 / 1M tokens
Blended Price (3:1)$3 / 1M tokens
Cache Read Price$0.5 / 1M tokens
Speed
Tokens/sec81.0
Time to First Token22.10s
Time to Answer22.10s
Provider Price Ranking
Provider Price Ranking
5 providers
Cheapest: xAIMost Expensive: Venice AI
ProviderInputOutput
1xAICheapest
$0
$0.00001
2SpaceXAIPRIMARY
$2
$6
3DevPass (LLM Gateway)
$2
$6
4Neon
$2
$6
5Venice AI
$2.27
$6.8
Compare pricing across different API providers for this model.