Benchmark Almanac

grok-code-fast-1

grok-code-fast-1 places in the top three on 2 benchmarks.

Released 28 Aug 2025
24
Benchmarks with a score
0
Ranked first, out of five or more models
2
In the top three
Unknown lab Aug 2025

grok-code-fast-1

No Epoch Capabilities Index score yet
  • Terminal-Bench 2.0 25.8% #36 /43
  • Toolathlon 18.5% #40 /50
  • Terminal-Bench 25.8% #12 /18

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Coding

BenchmarkScoreRankSource
SWE-bench Verified 70.8% #70 of 150 Model card
IOI (Vals) 4.33% #43 of 55 Official leaderboard
ALE-Bench 588 #95 of 121 Epoch AI
WeirdML 35.1% #94 of 112 Official leaderboard
CodeClash 1,006 #7 of 8 Official leaderboard
Code Arena 1,166 #122 of 124 Official leaderboard
WebDev Arena 1,165 #104 of 105 Epoch AI

Agents and tools

BenchmarkScoreRankSource
SnakeBench 28 #47 of 183 Official leaderboard
MCP-Universe 26.4% #11 of 30 Official leaderboard
MCPMark 20.5% #16 of 28 Official leaderboard
CompileBench 73.3% #12 of 20 Official leaderboard
Terminal-Bench 25.8% #12 of 18 Epoch AI
Pencil Puzzle Bench 0% #37 of 53 Official leaderboard
Toolathlon 18.5% #40 of 50 Official leaderboard
Terminal-Bench 2.0 25.8% #36 of 43 Official leaderboard

Safety and security

BenchmarkScoreRankSource
Refusals + System Jailbreak (xAI) 0% #1 of 4 Model card
General refusals (xAI) 0% #2 of 7 Model card
AgentHarm 17% #3 of 6 Model card
Refusals + User Jailbreak (xAI) 0% #2 of 4 Model card
MASK 71.9% #14 of 21 Model card
AgentDojo 26.9% #6 of 7 Model card
BioLP-bench 19.9% #8 of 9 Model card
Virology Capabilities Test (VCT) 28.7% #27 of 28 Model card
Cybench 22.5% #17 of 17 Model card

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.

Its system card

Every result in the longer documents the lab published with it. 10 of them aren't in the launch post.