RLTasksby ulam.ai
Models / xAI

xAI / MODEL EVIDENCE

Grok 4.1 Fast (Reasoning)

19 benchmarks · 23 observations · 23 sources · released 2025-11-19

Scores at a glance

19 benchmarks · large dot: Grok 4.1 Fast (Reasoning); small dots: closest models where reported

MMLU-Pro ↗85.37%
84.8689.76

Grok 4.1 Fast (Reasoning) · MMLU-Pro · AA implementation ↗

1 more reported result

84.18 % · Grok 4.1 Fast (Reasoning) · MMLU Pro · Accuracy · Vals AI · MMLU Pro ↗

LegalBench ↗82.45 %
32.9788.56

Grok 4.1 Fast (Reasoning) · LegalBench · Accuracy ↗

MedCode ↗28.08 %
19.7263.57

Grok 4.1 Fast (Reasoning) · MedCode · Accuracy ↗

MedScribe ↗78.73 %
4.2791.43

Grok 4.1 Fast (Reasoning) · MedScribe · Accuracy ↗

MMMU-Pro ↗72.66 %
22.7790.64

Grok 4.1 Fast (Reasoning) · MMMU Pro · Accuracy ↗

Vibe Code Bench ↗1.2 %
092.39

Grok 4.1 Fast (Reasoning) (OpenHands) · Vibe Code Bench · original task set ↗

ForecastBench ↗64.8 Brier index
46.467

grok-4-1-fast-reasoning† · Overall difficulty-adjusted Brier index ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

11.7 percentile-point gap

14 of 18 shared benchmark comparisons

18.5 percentile-point gap

11 of 18 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.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. LiveCodeBench Benchmark | Artificial Analysis ↗

    Artificial Analysis

  2. MMLU-Pro Benchmark | Artificial Analysis ↗

    Artificial Analysis

  3. Forecastbench — methodology and published results ↗

    Epoch AI · 2026

  4. AIME — evaluation methodology and results ↗

    Vals AI · 2026

  5. CaseLaw — evaluation methodology and results ↗

    Vals AI · 2026

  6. CorpFin — evaluation methodology and results ↗

    Vals AI · 2026

  7. GPQA Diamond — evaluation methodology and results ↗

    Vals AI · 2026

  8. LiveCodeBench — evaluation methodology and results ↗

    Vals AI · 2026

  9. LegalBench — evaluation methodology and results ↗

    Vals AI · 2026

  10. MedCode — evaluation methodology and results ↗

    Vals AI · 2026

  11. MedQA — evaluation methodology and results ↗

    Vals AI · 2026

  12. MedScribe — evaluation methodology and results ↗

    Vals AI · 2026

  13. MGSM — evaluation methodology and results ↗

    Vals AI · 2026

  14. MMLU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  15. MMMU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  16. MortgageTax — evaluation methodology and results ↗

    Vals AI · 2026

  17. Poker Agent — evaluation methodology and results ↗

    Vals AI · 2026

  18. Public Benefits Bench — evaluation methodology and results ↗

    Vals AI · 2026

  19. Public Benefits Bench v1 — evaluation methodology and results ↗

    Vals AI · 2026

  20. SAGE — evaluation methodology and results ↗

    Vals AI · 2026

  21. SWE-bench Verified — evaluation methodology and results ↗

    Vals AI · 2026

  22. TaxEval — evaluation methodology and results ↗

    Vals AI · 2026

  23. Vibe Code Bench — evaluation methodology and results ↗

    Vals AI · 2026

Names used in source tables

Grok 4.1 Fast (Reasoning) · Grok 4.1 Fast (Reasoning) (Mini-SWE-agent) · Grok 4.1 Fast (Reasoning) (OpenHands) · grok-4-1-fast-reasoning†