Frontier BenchAI model benchmarks · Jul 2026
ModelsCompareLabsMethodology
All models
X

Grok 4.1 Fast

xAI

Budget-tier coding leader. Cheapest credible agent for high-volume workloads.

Fast / CheapProprietary2M contextReleased Jan 2026textvisioncode

API price · per 1M tokens

$0.2/$0.5

input / output

≈ $0.28/M blended

Benchmarks

Bar shows this model's score; tick shows the best score across all tracked models for context.

SWE-bench VerifiedReal GitHub issues, human-verified patches. The standard coding-agent benchmark.
70.0/ best 90.1
GPQA DiamondGoogle-proof graduate-level science Q&A. General reasoning proxy.
68.0/ best 94.4
MMLU-ProMulti-task language understanding across 120+ academic subjects.
76.0/ best 93.0
HumanEval+Functional code generation from docstrings.
90.5/ best 96.0
MATH-500Competition-style math problems.
93.0/ best 97.8

Other xAI models

X

Grok 4.20

Frontier

≈$3.00/M

Built by GLM-5.2 · Scores are directional, drawn from public mid-2026 benchmarks.

SWE-bench, GPQA, MMLU, AIME, HLE etc. are trademarks of their respective owners.