Summary
- Answers 33 of 80 verification questions correctly (41.2%), placing #54 of 72 models tested on the current suite.
- Generates 7 output tokens per second, faster than 0% of the models we measure.
- Starts responding after 1.1 s (median time to first token), including thinking time.
- Costs $0.00061 per question as billed, #10 cheapest of 12 models priced under $0.15 per 1M tokens.