fix(lab): price deepseek cache reads at 0.02x, not 0.1x

↗ view on GitHub · Eli Ziff · 2026-08-07 · 37e7fa19

DeepSeek charges cache hits at 2% of the miss rate ($0.0028/M vs
$0.14/M - 50x discount), not the Anthropic-style 10% the harness
assumed. Coding arms carry ~3x the cache_read of native (round
re-serving), so the 0.1x rate inflated their cost premium ~5x.

- lab-beaver-arm: lane-aware cacheReadMultiplier (0.02 deepseek,
  0.1 else) in cache_adjusted* and cached_read_multiplier metadata
- lab-compare: recompute deepseek cost from components at 0.02x
  (stored field still bakes old 0.1x into historical runs); model
  derived from run dir slug

Pooled reqecho vs native (5 tasks, 334 criteria): +7 at 1.42x
reported -> 1.20x at the real rate (C@1 729k vs 605k). Score and
wall-clock rows unchanged.

Co-Authored-By: Claude <noreply@anthropic.com>
Repository eliziff/Beaver
Author Eli Ziff <eliasziff@gmail.com>
Authored
Parents f535eb27
Stats 2 files changed , +39 , -19
Part of Evaluation harness: Beaver-CAN and LegalBench-RAG adapters

Capture this commit into my fork

Download a Markdown prompt that tells Claude how to port this exact commit into your working tree. Run it via claude -p < capture-commit-37e7fa19.md from inside the repo you want the change in.

⬇ Download capture-commit-37e7fa19.md