Me
llama-3.3-70b-instruct-fp8-fast Benchmark & Insights
Meta Cloudflare Workers AI
Updated Jul 31, 2026 All models
Sample size
169 runs
in window
Accuracy
77.4%
consensus match · 177d
Confidence
88%
over 178 runs
Window end
Jul 31, 2026
most recent run
Input price
$0.29/MTok
prompt tokens
Output price
$2.25/MTok
completion tokens
Model insights
- 01 The only model that errs in both directions in nearly equal measure, which makes it noisy rather than biased — there is no offset that fixes it.
- 02 It skips "medium" almost entirely, swinging between "low" and "high", and it turned from over-warning in February through May to under-warning across June and July.
Recent forecasts