xAI

Grok-1.5

Zero-eval

by xAI

+
+
+
+
About

Grok 1.5 was developed by xAI as an advanced language model, designed to provide helpful and accurate information with a focus on reasoning and factual knowledge. Built to serve as a conversational AI with strong analytical capabilities, it represents xAI's early generation of foundation models.

+
+
+
+
Timeline
AnnouncedMar 28, 2024
ReleasedMar 28, 2024
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown

Overall Performance

9 benchmarks
Average Score
63.9%
Best Score
90.0%
High Performers (80%+)
3
+
+
+
+
All Benchmark Results for Grok-1.5
Complete list of benchmark scores with detailed information
GSM8k
text
0.90
90.0%
Self-reported
DocVQA
multimodal
0.86
85.6%
Self-reported
MMLU
text
0.81
81.3%
Self-reported
HumanEval
text
0.74
74.1%
Self-reported
MMMU
multimodal
0.54
53.6%
Self-reported
MathVista
multimodal
0.53
52.8%
Self-reported
MMLU-Pro
text
0.51
51.0%
Self-reported
MATH
text
0.51
50.6%
Self-reported
GPQA
text
0.36
35.9%
Self-reported
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+