← Back to all models
G

Grok 3

by xAI
Flagship Paid API Multimodal 🏆 Ranked #4 of 85
90.6
Overall Score
out of 100
About

xAI's most capable model, trained on a 100,000-GPU cluster and setting new benchmarks in mathematics and scientific reasoning. Grok 3 integrates real-time data from the X platform and leads the Arena ELO leaderboard among commercial models.

Key Metrics
Context Window
131K
tokens
Avg Response
900
milliseconds
Input Cost
$3.0
per million tokens
Output Cost
$15.0
per million tokens
Arena ELO
1402
Chatbot Arena rating
MT-Bench
9.2
out of 10
Benchmark Scores
MMLU
93.3%
HumanEval
91.8%
MATH
93.3%
GPQA
72.0%
MT-Bench
92.0/10
Capability Profile
Strengths & Limitations
Strengths
✓ State-of-the-art reasoning ✓ Top Arena ELO ✓ Real-time data access ✓ Exceptional mathematics ✓ Strong coding
Limitations
⚠ High cost ⚠ Tied to X ecosystem ⚠ Less safety filtering than Anthropic
Ideal Use Cases
Advanced research Competitive mathematics Code generation Real-time analysis Complex reasoning
Model Details
Provider xAI
Released 2025-02-17
Type Paid API
Multimodal Yes
Tier Flagship
Global rank #4 / 85
Pricing (USD)
Input tokens $3.0/M
Output tokens $15.0/M
Per 1,000 tokens ≈ $0.0030 input / $0.0150 output
All Benchmarks
MMLU 93.3%
HumanEval 91.8%
MATH 93.3%
GPQA 72.0%
MT-Bench 9.2/10
Arena ELO 1402
Compare this model View Rankings

You might also consider