- Scored runs
- 2
- Run log entries
- 3
RecordIdentifier
k2-3.7b
Every result below is as recorded. Without a written entry there is no stated reason for the test and no verdict.
Recorded runs2 scored · 95% intervals
| Suite | Score | 95% interval | Passed | Runtime · profile | Recorded |
|---|---|---|---|---|---|
| synthesis | 58.3% | 45.7–69.9 | Passed 35/60 | llama.cppextraction | 2026-09-09 |
| worldview | 50.0% | 35.2–64.8 | Passed 20/40 | llama.cppextraction | 2026-09-09 |
Runs marked unenforced were measured through mlx_lm on a suite that requires constrained decoding. mlx_lm accepts the schema and ignores it, so those numbers do not measure what the suite is designed to measure. They are kept and labelled rather than deleted.
Every run log entry for this model (3)
| Finished | Suite | Runtime · profile | Score | Coverage | Grader · dataset · config |
|---|---|---|---|---|---|
| worldviewworldview/2 | not recordedextraction | 50.0% | Coverage 40/40 | g 9acfba1b704feb28d e97835de9e6fc227c 13dc41ad1b2821d9 | |
| synthesissynthesis/2 | not recordedextraction | 58.3% | Coverage 60/60 | g 4156dd3c13361e8bd 267d1954e225c5b6c be9a405fa957d750 | |
| synthesissynthesis/1 | not recordedextraction | 86.7% | Coverage 60/60 | g 27df090db4445c2cd 760936a5348b2ffdc cc272a124c5d1351 |
Findings3 that name this model
- 2026-09-20Typed decisions split across a routing table, not a winner; the only arm you can put a threshold on matters more than the most accurate one
- 2026-09-19A 34 MB model routes tool calls in ~110 ms but fires on small talk, misses jargon, and scrambles any extraction with more than two roles
- 2026-09-10Tool perception is binary and tracks the checkpoint, not size or vendor claims