LegalBench ↗79.11 %
Grok 4.1 Fast Non-Reasoning · LegalBench · Accuracy ↗
xAI / MODEL EVIDENCE
Grok 4.1 Fast Non-Reasoning
13 benchmarks · 14 observations · 14 sources
Scores at a glance
13 benchmarks · large dot: Grok 4.1 Fast Non-Reasoning; small dots: closest models where reported
CorpFin v2 ↗52.49 %
Grok 4.1 Fast Non-Reasoning · CorpFin · Accuracy ↗
MortgageTax & TaxEval v2 ↗34.26 %
Grok 4.1 Fast Non-Reasoning · MortgageTax · Accuracy ↗
1 more reported result
61.86 % · Grok 4.1 Fast Non-Reasoning · TaxEval · Accuracy · Vals AI · TaxEval ↗
MedCode ↗28.35 %
Grok 4.1 Fast Non-Reasoning · MedCode · Accuracy ↗
MedScribe ↗77.46 %
Grok 4.1 Fast Non-Reasoning · MedScribe · Accuracy ↗
MedQA (USMLE) ↗76.03 %
Grok 4.1 Fast Non-Reasoning · MedQA · Accuracy ↗
AIME 2024–2025 · Vals ↗27.08 %
Grok 4.1 Fast Non-Reasoning · AIME · Accuracy ↗
MGSM (Multilingual GSM) ↗87.56 %
Grok 4.1 Fast Non-Reasoning · MGSM · Accuracy ↗
GPQA Diamond ↗65.15 %
Grok 4.1 Fast Non-Reasoning · GPQA Diamond · Accuracy ↗
MMLU-Pro ↗75.21 %
Grok 4.1 Fast Non-Reasoning · MMLU Pro · Accuracy ↗
MMMU-Pro ↗63.7 %
Grok 4.1 Fast Non-Reasoning · MMMU Pro · Accuracy ↗
Grok 4.1 Fast Non-Reasoning · SAGE · Accuracy ↗
LiveCodeBench ↗42.62 %
Grok 4.1 Fast Non-Reasoning · LiveCodeBench · Accuracy ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
13 of 13 shared benchmark comparisons
Command A →Cohere
8 of 13 shared benchmark comparisons
Gemini 1.5 Pro (002) →Google
10 of 13 shared benchmark comparisons
How similarity is measured
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- AIME — evaluation methodology and results ↗
- CorpFin — evaluation methodology and results ↗
- GPQA Diamond — evaluation methodology and results ↗
- LiveCodeBench — evaluation methodology and results ↗
- LegalBench — evaluation methodology and results ↗
- MedCode — evaluation methodology and results ↗
- MedQA — evaluation methodology and results ↗
- MedScribe — evaluation methodology and results ↗
- MGSM — evaluation methodology and results ↗
- MMLU Pro — evaluation methodology and results ↗
- MMMU Pro — evaluation methodology and results ↗
- MortgageTax — evaluation methodology and results ↗
- SAGE — evaluation methodology and results ↗
- TaxEval — evaluation methodology and results ↗
Names used in source tables
Grok 4.1 Fast Non-Reasoning