AI Model Timeline

Tracking the accelerating release frequency of frontier AI models.

Grok Code Fast

X.AI·

LLMscodingcloud

Overview

Specialized high-speed coding model.

Capabilities and innovations

Instant code genRepo-level understandingTest driven dev

Benchmarks

BenchmarkScoreSource
GPQA Diamond79.5%unsourced
Humanity’s Last Exam (no tools)22.8%unsourced
SWE-bench Verified68.3%unsourced
MMLU88.9%unsourced
  • SWE-bench Pro: not reported by the vendor
  • MMLU-Pro: not reported by the vendor
  • Terminal-Bench 2.x: benchmark did not exist at release
  • MMMU-Pro: benchmark did not exist at release

Links

More from X.AI

Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.