Compare Models
Grok 4.6

Release Date: Aug 12, 2026

Developer SpaceXAI  🇺🇸
Context Window 500k
Max Output Tokens 500k
Token Costs (in/out) $2.00/6.00
Weights Private
Input Modalities

Accuracy

59.17 % ± 1.21

Cost / Test (Vals Index)

$ 4.335

Latency

38 min 4 s

Vals Index
BenchmarksAccuracyRankings
Vals Index

0.0%

±1.21
19/65
Vals RSI Index

0.0%

10/19
Code Migration

0.0%

±4.48
14/67
CyberBench v1.1

0.0%

±5.90
4/7
EMB

0.0%

±3.08
24/65
Finance Agent (v2)

0.0%

±0.67
25/68
Time Horizon Index: KSP

0.0%

±0.00
10/11
Legal Research Bench

0.0%

±3.47
7/68
MedCode

0.0%

±2.26
34/98
MedScribe

0.0%

±1.96
17/100
MortgageTax

0.0%

±0.95
47/98
MysteryMechanism

0.0%

±3.10
8/14
ProofBench v1.1

0.0%

±5.02
20/38
SAGE

0.0%

±3.08
78/85
Public Benefits Bench v1.1

0.0%

±1.23
11/40
Tax Agent Bench

0.0%

±3.00
5/26
TaxEval v2

0.0%

±0.90
87/145
Vibe Code Bench 1-100

0.0%

±3.17
15/20
Vibe Code Bench v1.1

0.0%

±3.82
25/103
BioMysteryBench

0.0%

±0.00
5/16
Harvey's Legal Agent Benchmark

0.0%

±2.65
6/69
GPQA Diamond

0.0%

±1.13
3/138
IOI

0.0%

±2.09
21/32
LiveCodeBench

0.0%

±0.94
7/143
LegalBench

0.0%

±0.42
12/147
MMLU Pro

0.0%

±0.30
11/138
SkillsBench

0.0%

±4.84
13/35
SWE-bench

0.0%

±0.92
4/88
Terminal-Bench 4.0

0.0%

±2.81
13/32
Terminal-Bench Science

0.0%

±2.44
16/29
Proprietary BenchmarksAcademic BenchmarksIndustry Partners
Vals
Default Provider : SpaceXAI
Temperature: 0.7
Top P: 0.95
Top K: Default
Max Output Tokens: 500,000
Reasoning Effort: high