Grok-3
Multimodal
Zero-eval
#3AIME 2024
#3LiveCodeBench
by xAI
+
+
+
+
About
Grok-3 is a multimodal language model developed by xAI. This model demonstrates exceptional performance with an average score of 85.7% across 5 benchmarks. It excels particularly in AIME 2025 (93.3%), AIME 2024 (93.3%), GPQA (84.6%). 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 2025, it represents xAI's latest advancement in AI technology.
+
+
+
+
Pricing Range
Input (per 1M)$3.00 -$3.00
Output (per 1M)$15.00 -$15.00
Providers1
+
+
+
+
Timeline
AnnouncedFeb 17, 2025
ReleasedFeb 17, 2025
Knowledge CutoffNov 17, 2024
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown
Overall Performance
5 benchmarks
Average Score
85.7%
Best Score
93.3%
High Performers (80%+)
3Performance Metrics
Max Context Window
136.0KAvg Throughput
100.0 tok/sAvg Latency
1ms+
+
+
+
All Benchmark Results for Grok-3
Complete list of benchmark scores with detailed information
| AIME 2025 | text | 0.93 | 93.3% | Self-reported | |
| AIME 2024 | text | 0.93 | 93.3% | Self-reported | |
| GPQA | text | 0.85 | 84.6% | Self-reported | |
| LiveCodeBench | text | 0.79 | 79.4% | Self-reported | |
| MMMU | multimodal | 0.78 | 78.0% | Self-reported |