Summary
- Answers 60 of 80 verification questions correctly (75.0%), placing #15 of 72 models tested on the current suite.
- Generates 101 output tokens per second, faster than 48% of the models we measure.
- Starts responding after 1.1 s (median time to first token), including thinking time.
- Costs $0.0063 per question as billed, #14 cheapest of 31 models priced over $1 per 1M tokens.