Codesota · Models · Grok-4-FastxAI7 results · 1 benchmarks
Model card

Grok-4-Fast.

xAIopen-source
§ 01 · Benchmarks

Every benchmark Grok-4-Fast has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01PLCCNatural Language Processing · Polish Cultural Competencygrammar72.0%#42/165source ↗
02PLCCNatural Language Processing · Polish Cultural Competencyhistory81.0%#60/165source ↗
03PLCCNatural Language Processing · Polish Cultural Competencygeography79.0%#61/165source ↗
04PLCCNatural Language Processing · Polish Cultural Competencyaverage70.2%#63/165source ↗
05PLCCNatural Language Processing · Polish Cultural Competencyculture-and-tradition71.0%#66/165source ↗
06PLCCNatural Language Processing · Polish Cultural Competencyart-and-entertainment59.0%#68/165source ↗
07PLCCNatural Language Processing · Polish Cultural Competencyvocabulary59.0%#75/165source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area

Where Grok-4-Fast actually performs.

Natural Language Processing
1
benchmark
avg rank #62.1
§ 04 · Related models

Other xAI models scored on Codesota.

Grok 2
4 results
Grok 4
4 results
Grok 3
1 result
Grok Code Fast 1
1 result
Grok-2-1212
0 results
Grok-3-Beta
0 results
Grok-3-Mini-Beta
0 results
Grok-4.1-Fast
0 results
§ 05 · Sources & freshness

Where these numbers come from.

sdadas/PLCC
7
results
7 of 7 rows marked verified.