Model
Model explorer
Grok 4.7
CLOSEDSpaceXAI · Grok 4.7 family · released Sep 16, 2026
SpaceXAI's September 16, 2026 point release — Grok 4.6's successor at an unchanged $2/$6 per Mtok. The launch table is a straight line over 4.6's: GDPval-AA +43, AA Briefcase +44, DeepSWE +3.5, CursorBench +3.9, Terminal-Bench 3 +3.7, with a first-time ExploitBench row (44.8) replacing the marketing-speak with a defensive-security number. No major capability claims beyond 'fastest frontier agent on our harness'; the honest read is a steady monthly cadence keeping Grok roughly level with Sonnet-class mid-frontier models rather than contesting Astra/Fable at the top.
ReasoningCodingVisionFunction callingTool useAgentic
2990.7
Elo · rank #8
Parameters
Undisclosed
Active params
Undisclosed
Context
500K tokens
Architecture
Proprietary sparse-MoE reasoning model (undisclosed size); 500K-token context
License
Proprietary
Languages
—
API price (in/out)
$2 / $6
Modalities
text · vision
Benchmark results
Bar shows position within the tracked field; marker = field best
best: Claude Opus 5 · 1720
best: this model · 73.8%
best: Muse Spark 1.3 · 75.4%
best: GPT-6 Astra · 100.0%
best: Claude Fable 5 · 64.9%
best: Claude Fable 5 · 1932
best: GPT-6 Astra · 96.0%
best: this model · 17.2%
best: GPT-5.6 Sol · 34.6%
Run it locally
Closed weights — available via API only. No local deployment.
Input / M tok
$2
Output / M tok
$6
API price $2/$6 · each benchmark row carries its own source badge (see methodology)