← Back to all models
G

Grok-2

by xAI
Flagship Proprietary Multimodal 🏆 Ranked #15 of 22
77.3
Overall Score
out of 100
About

xAI's flagship model, built with real-time access to information from the X platform. Grok-2 takes a distinctive approach to AI with a more candid, less filtered personality and strong performance on complex reasoning tasks.

Key Metrics
Context Window
131K
tokens
Avg Response
890
milliseconds
Input Cost
$2.0
per million tokens
Output Cost
$10.0
per million tokens
Arena ELO
1248
Chatbot Arena rating
MT-Bench
8.7
out of 10
Benchmark Scores
MMLU
87.5%
HumanEval
88.4%
MATH
76.1%
GPQA
56.0%
MT-Bench
87.0/10
Capability Profile
Strengths & Limitations
Strengths
✓ Real-time information access ✓ Strong reasoning ✓ Less filtered responses ✓ X platform integration ✓ Vision capabilities
Limitations
⚠ Tied to X ecosystem ⚠ Less safety filtering ⚠ Smaller community
Ideal Use Cases
Current events analysis Social media insights Research Code generation Creative tasks
Model Details
Provider xAI
Released 2024-08-13
Open source No
Multimodal Yes
Tier Flagship
Global rank #15 / 22
Pricing (USD)
Input tokens $2.0/M
Output tokens $10.0/M
Per 1,000 tokens ≈ $0.0020 input / $0.0100 output
All Benchmarks
MMLU 87.5%
HumanEval 88.4%
MATH 76.1%
GPQA 56.0%
MT-Bench 8.7/10
Arena ELO 1248
Compare this model View leaderboard

You might also consider