Me
llama-3.3-70b-instruct-fp8-fast Benchmark & Insights
Meta Cloudflare Workers AI
Updated Jul 18, 2026 All models
Sample size
156 runs
in window
Accuracy
74.4%
consensus match · 160d
Confidence
88%
over 161 runs
Window end
Jul 18, 2026
most recent run
Input price
$0.29/MTok
prompt tokens
Output price
$2.25/MTok
completion tokens
Model insights
- 01 The panel's most erratic model, missing in both directions almost equally (25 under, 22 over) with 15 false "unsafe" alarms and, on 2026-07-18, a false "safe" on a consensus-"high" day.
- 02 Since late June it has flipped into a near-daily "low"-vs-"medium" optimism streak.
Recent forecasts