mantis5x5

Cache hit rate

97%

Input served from cache

Higher than 81% of developers

Cache reuse

300.3×

Reads per cached token

Higher than 95% of developers

Cost per 1M tokens

$1.43

Blended cost across all tokens

Lower than 18% of developers

Output share

1%

Tokens generated as output

Higher than 97% of developers

Parallel tools

34%

Days with 2+ tools · 1.4 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

2.4

Distinct models used each day

Daily cost variation

6.3

Coefficient of variation; lower is steadier

Active days in span

75%

First to last active day