xAIproprietary
Released: 2026-08-12

Grok 4.6

xAI latest Colossus-trained frontier flagship optimized for long agentic jobs, tool use, and real-time reasoning.

Intelligence Index
93.0/ 100
Calibrated multi-domain composite
Throughput Speed
75tok/sec
Output streaming throughput
Time To First Token
380ms
Initial chunk server latency
LiveBench Contam-Free
78.5%
September 2026 suite score

LiveBench Multi-Domain Evaluation Breakdown

Monthly refreshed contamination-free test sets
Logical Reasoning88.4%
Coding & Repo Repair80.2%
Mathematics (AIME)92.1%
Data Analysis & Tables75.8%
Language & Comprehension70.9%
Instruction Following65.1%

Sourced Benchmark Evaluations (3)

Verified performance across authoritative benchmarks with provenance tracking.
BenchmarkStatusScoreTrustDateSource TypeProvenance
ARC-AGI-2Nearing Saturation72.9%
75
2026-09-09independentSource ↗
SWE-bench VerifiedSaturated61%
25
2026-08-21independentSource ↗
IFEvalDeprecated65.1%
25
2026-08-16independentSource ↗
OpenAI Compatible API ExecutionAPI Ready
from openai import OpenAI

client = OpenAI()
response = client.chat.completions.create(
    model="grok-4-6",
    messages=[{"role": "user", "content": "Evaluate multi-step logic problem"}],
    temperature=0.2
)
print(response.choices[0].message.content)

Evaluation & Sourcing Notes

Scores listed for Grok 4.6 represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.

All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.