bench: discovery-bound suite — paraphrase/absence/survey tasks isolate the listing's structural advantage

Browse Source

Bridge vs listing only (Opus 4.8, 830 real UE schemas, 3 reps/cell).
Excluding one both-modes mock artifact: listing 24/24 vs bridge 20/24,
searches/task 0.2 vs 4.0. Bridge failures: core-tool substitution at
frontier tier (ran the host test suite via terminal instead of
discovering RunTests, 2/3 reps), up to 8 searches to prove a negative,
and search-vocabulary misses on paraphrase. Listing asserts absence in
zero searches and answers a 5-way capability survey in 1 API call.

...

This commit is contained in:

teknium1

2026-07-19 01:41:46 -07:00

committed by Teknium

parent 21cc643ac2

commit 2643ea17fb

2 changed files with 1543 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

mcp-research-data/ue_discovery_rows.json

+1309

File diff suppressed because it is too large Load Diff