For Evaluation on AIME2025, GPQA, LSAT and MMLU, you can use scripts in scripts/eval: python scripts/eval/generate_aime.py python scripts/eval/generate_gpqa.py python ...
The system employs a MESI protocol to ensure cache coherence. L1 instruction cache is four-way set associative and consists of 16K sets and 64-byte lines. L1 data cache is eight-way set associative ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback