Grok-2
Multimodal
Zero-eval
by xAI
About
Grok-2 is a multimodal language model developed by xAI. It achieves strong performance with an average score of 76.5% across 8 benchmarks. It excels particularly in DocVQA (93.6%), HumanEval (88.4%), MMLU (87.5%). It supports a 136K token context window for handling large documents. The model is available through 1 API provider. As a multimodal model, it can process and understand text, images, and other input formats seamlessly. Released in 2024, it represents xAI's latest advancement in AI technology.
Pricing Range
Input (per 1M)$2.00 -$2.00
Output (per 1M)$10.00 -$10.00
Providers1
Timeline
AnnouncedAug 13, 2024
ReleasedAug 13, 2024
Specifications
Capabilities
Multimodal
License & Family
License
Proprietary
Benchmark Performance Overview
Performance metrics and category breakdown
Overall Performance
8 benchmarks
Average Score
76.5%
Best Score
93.6%
High Performers (80%+)
3Performance Metrics
Max Context Window
136.0KAvg Throughput
85.0 tok/sAvg Latency
1msTop Categories
code
88.4%
vision
79.8%
general
73.0%
math
72.5%
Benchmark Performance
Top benchmark scores with normalized values (0-100%)
Ranking Across Benchmarks
Position relative to other models on each benchmark
DocVQA
Rank #9 of 26
#6Llama 4 Scout
94.4%
#7Llama 4 Maverick
94.4%
#8Qwen2.5 VL 32B Instruct
94.8%
#9Grok-2
93.6%
#10Nova Pro
93.5%
#11DeepSeek VL2
93.3%
#12Pixtral Large
93.3%
HumanEval
Rank #18 of 62
#15Llama 3.3 70B Instruct
88.4%
#16Mistral Small 3.1 24B Instruct
88.4%
#17DeepSeek-V2.5
89.0%
#18Grok-2
88.4%
#19Qwen2.5-Coder 7B Instruct
88.4%
#20Qwen2.5 32B Instruct
88.4%
#21o1
88.1%
MMLU
Rank #15 of 78
#12GPT-4.1 mini
87.5%
#13Kimi K2 Base
87.8%
#14Qwen3 235B A22B
87.8%
#15Grok-2
87.5%
#16Kimi-k1.5
87.4%
#17Llama 3.1 405B Instruct
87.3%
#18o3-mini
86.9%
MATH
Rank #20 of 63
#17GPT-4o
76.6%
#18Nova Pro
76.6%
#19Llama 3.3 70B Instruct
77.0%
#20Grok-2
76.1%
#21Gemma 3 4B
75.6%
#22Qwen2.5 7B Instruct
75.5%
#23DeepSeek-V2.5
74.7%
MMLU-Pro
Rank #13 of 60
#10Gemini 1.5 Pro
75.8%
#11DeepSeek-V3
75.9%
#12Phi 4 Reasoning Plus
76.0%
#13Grok-2
75.5%
#14GPT-4o
74.7%
#15Phi 4 Reasoning
74.3%
#16Llama 4 Scout
74.3%
All Benchmark Results for Grok-2
Complete list of benchmark scores with detailed information
DocVQA DocVQA benchmark | vision | multimodal | 0.94 | 93.6% | Self-reported |
HumanEval HumanEval benchmark | code | text | 0.88 | 88.4% | Self-reported |
MMLU MMLU benchmark | general | text | 0.88 | 87.5% | Self-reported |
MATH MATH benchmark | math | text | 0.76 | 76.1% | Self-reported |
MMLU-Pro MMLU-Pro benchmark | general | text | 0.76 | 75.5% | Self-reported |
MathVista MathVista benchmark | math | text | 0.69 | 69.0% | Self-reported |
MMMU MMMU benchmark | vision | multimodal | 0.66 | 66.1% | Self-reported |
GPQA GPQA benchmark | general | text | 0.56 | 56.0% | Self-reported |
Resources