Grok-1.5
An advanced language model with improved reasoning capabilities, particularly excelling in coding and mathematical tasks. Features a 128K token context window and enhanced problem-solving abilities compared to its predecessor.
Benchmark results
| Benchmark | Score | Tags | Source |
|---|---|---|---|
| DocVQA | 85.6% | self-reported llm-stats | link → |
| GPQA | 35.9% | self-reported llm-stats | link → |
| GSM8k | 90.0% | self-reported llm-stats | link → |
| HumanEval | 74.1% | self-reported llm-stats | link → |
| MATH | 50.6% | self-reported llm-stats | link → |
| MathVista | 52.8% | self-reported llm-stats | link → |
| MMLU | 81.3% | self-reported llm-stats | link → |
| MMLU-Pro | 51.0% | self-reported llm-stats | link → |
| MMMU | 53.6% | self-reported llm-stats | link → |