Compare Models

Grok 4.1 Fast (Reasoning)

Grok 4.1 Fast (Reasoning) is a model from SpaceXAI, released November 19, 2025. Its best result is #71 of 151 on LegalBench.

Release Date: Nov 19, 2025

Developer SpaceXAI  🇺🇸
Context Window 2M
Max Output Tokens 2M
Token Costs (in/out) $0.20/0.50
Weights Private
Input Modalities

Accuracy

55.02 %

Avg. Cost (In/Out)

$ 0.20 / $ 0.50

Latency

2 min 9 s

Vals Index
BenchmarksAccuracyRankings
MedCode

28.08%

±1.99
101/107
MedScribe

78.73%

±1.87
64/109
MortgageTax

42.61%

±0.95
90/98
SAGE

31.33%

±3.02
78/91
Public Benefits Bench v1.1

44.79%

±1.29
48/50
TaxEval v2

73.14%

±0.86
52/145
Vibe Code Bench v1.1

1.20%

±1.20
108/113
GPQA Diamond

84.34%

±1.85
53/138
LiveCodeBench

80.64%

±1.09
67/143
LegalBench

82.45%

±0.46
71/151
MMLU Pro

84.18%

±0.36
67/138
MMMU Pro

72.66%

±1.07
62/93
SWE-bench

41.40%

±2.21
85/88
Terminal-Bench 2.0

24.72%

±4.60
52/67
Proprietary BenchmarksAcademic BenchmarksIndustry Partners
Vals
Default Provider : SpaceXAI
Temperature: 0.7
Top P: 0.95
Top K: Default
Max Output Tokens: 2,000,000

Updates

Nov 19, 2025

We just evaluated Grok 4.1 Fast (Reasoning) and Grok 4.1 Fast Non-Reasoning on all benchmarks!

We found that the reasoning variant consistently outperforms the non-reasoning variant - see our comparison page. Grok 4.1 Fast Non-Reasoning struggles - its best performance is tenth place on our IOI v1 benchmark, while Grok 4.1 Fast (Reasoning) achieves strong performance across the board, placing third on our CorpFin benchmark.

Both models perform similarly to their predecessors - see our comparison pages for both the reasoning and non-reasoning variants. Like their predecessors, both models are also extremely cost-efficient on a per-token basis.

Congratulations to the SpaceXAI team for the launch of Grok 4.1!