Model card: half the tokens, average accuracy within half a point

README.md

@@ -12,10 +12,10 @@ tags:
 
 <img src="thinklite-banner.png?v=2" alt="Thinklite-27B: Qwen 3.8 27B made efficient" style="width:100%;max-width:100%;height:auto;display:block;margin-bottom:1em;" />
 
-**Qwen3.8-27B that thinks with half the tokens at near-identical accuracy.** At `reasoning_effort="xhigh"`,
-Thinklite-27B uses 47% less reasoning than Qwen3.8-27B on average over six benchmarks and writes half as many output
-tokens, so its time-to-final-output (TTFO) is about 2x shorter, while its average accuracy stays within half a point
-of the base model (89.8 vs 90.2). At `reasoning_effort="low"` it uses 28% less reasoning, at an average accuracy 2.2
+**Qwen3.8-27B that thinks with half the tokens, with average accuracy within half a point.** At
+`reasoning_effort="xhigh"`, Thinklite-27B uses 47% less reasoning than Qwen3.8-27B on average over six benchmarks and
+writes half as many output tokens, so its time-to-final-output (TTFO) is about 2x shorter, at an average accuracy of
+89.8 against the base model's 90.2. At `reasoning_effort="low"` it uses 28% less reasoning, at an average accuracy 2.2
 points below the base model.
 
 <style>