Model record

Grok 4.20

xAI · released Mar 10, 2026

Overall standing

Overall
50.2rank 27 of 62
50.2 is at approximately the 57th percentile of the ranked Overall field. The field spans 19.0 to 62.2, with a median of 48.9.
6 of 8 measured · 2 estimated
Category standingsReasoning 65.6Coding —Math 6.6Agentic —
Reasoning
65.6rank 26 of 62
65.6 is at approximately the 59th percentile of the ranked Reasoning field. The field spans 31.6 to 73.3, with a median of 64.8.
4 of 4 measured
Coding
Insufficient data
1 of 2 measured
Math
6.6rank 30 of 62
6.6 is at approximately the 52th percentile of the ranked Math field. The field spans 0.0 to 32.3, with a median of 5.3.
1 of 1 measured
Agentic
Insufficient data
0 of 1 measured
Model factsClosed weights · $1.3 / $2.5 per 1M

Copied from the linked provider page; no separate retrieval date is stored.

Provider
xAI
Released
Weights
Closed weights
Context window
1,000,000 tokens
Input price / Mtok
$1.3
Output price / Mtok
$2.5
Reasoning effort
Not listed

Scores and sources

Measured scores retain their source and retrieval date. Missing scores are not treated as zero.

Benchmark scores, evaluation settings, sources, and retrieval dates for Grok 4.20
BenchmarkCategoryScoreEvaluation settingsSource
Terminal-Bench v2.1Coding—Not measured in this datasetNo source
τ³-BankingAgentic—Not measured in this datasetNo source
AA-LCRReasoning58.0Artificial Analysis independent run; 100 roughly 100k-token multi-document questions; 3 repeats; equality-checker pass@1; no toolsOpen source (opens in a new tab)
Humanity's Last ExamReasoning32.2Artificial Analysis independent run; 2,158 text-only questions; pass@1; GPT-4o (August 2024) equality checker; no toolsOpen source (opens in a new tab)
GPQA DiamondReasoning91.1Artificial Analysis independent run; 198 questions; 5 repeats; regex-graded pass@1; no toolsOpen source (opens in a new tab)
SciCodeCoding45.6Artificial Analysis independent run; 288 test subproblems; scientist background included; 3 repeats; subproblem pass@1Open source (opens in a new tab)
IFBenchReasoning81.2Artificial Analysis independent run; 294 single-turn prompts; 5 repeats; official loose evaluator; prompt-level pass@1Open source (opens in a new tab)
CritPtMath6.6Artificial Analysis independent run; 70 test challenges; 5 repeats; two-step answer parsing; official CritPt grader; pass@1; no toolsOpen source (opens in a new tab)