HNHacker News·
Archived topic · source no longer tracked
Mercury 2.5 LLM hits 770 tokens per second
The Mercury 2.5 LLM achieves an output speed of 770 tokens per second, as reported by artificialanalysis.ai. This performance is evaluated using the Artificial Analysis Intelligence Index v4.3.2, which incorporates 10 different evaluations. These evaluations include AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, and AA-LCR v1.1. The answer time is measured by the time taken to generate 500 output tokens.
Time & source
Times shown in UTC
Display time zone: UTC
Local time zone unavailable; showing UTC.
IngestedOffset at this time: UTC+0Sep 24, 2026, 00:01 UTC
- Ingested
- Sep 24, 2026, 00:01
- Source type
- Unclassified
- Basis
- Running about 2.2× the median of this source's recent listed items
- Triggering item
- Mercury 2.5 LLM hits 770 tokens per second
- Metric comparison
- 121 vs median 54.5 (20 baseline samples)
- Detected
- 09/24, 12:02
Full text isn't available here.
Read at source →