Me
llama-3.3-70b-instruct-fp8-fast
Benchmark & Insights
Meta Cloudflare Workers AI
Updated Oct 4, 2026 All models
Sample size
232 runs
in window
Accuracy
64.9%
reference match · 251d
Confidence
89%
over 252 runs
Window end
Oct 4, 2026
most recent run
Input price
$0.29/MTok
prompt tokens
Output price
$2.25/MTok
completion tokens
Model insights
- 01 Wrong in both directions: it leans low, calling 42 "MEDIUM_SAFE" days "low", yet raised 17 false alarms.
- 02 It also missed 11 "unsafe" days, including some only a few models missed (2026-07-18).
- 03 Scored 40-50% in February and March.
Recent forecasts