AG News
Kai and Jev on the same 400 questions of AG News, one run per Kai revision.
History
12 results across 2 metrics, newest first. Superseded runs stay, so a revision's progress can be read.
| Measured | Subject | Metric | Value | Baseline | Result | Status |
|---|---|---|---|---|---|---|
| Oct 16, 2026 | kai-1.4 · c1856a77 | Accuracy | 93.8% | Jev 86.0% | Win | Live · Hanzo-measured |
| Oct 16, 2026 | kai-1.4 · c1856a77 | Calibration error (ECE) | 0.022 | Jev 0.102 | Win | Live · Hanzo-measured |
| Oct 3, 2026 | kai-1 · 0834a74f | Accuracy | 94.3% | Jev 86.0% | Win | Superseded · Hanzo-measured |
| Oct 3, 2026 | kai-1 · 0834a74f | Calibration error (ECE) | 0.033 | Jev 0.102 | Win | Superseded · Hanzo-measured |
| Sep 28, 2026 | Kai a8 · 0cfeef05 | Accuracy | 94.3% | Jev 86.0% | Win | Superseded · Hanzo-measured |
| Sep 28, 2026 | Kai a7 · 0834a74f | Accuracy | 94.3% | Jev 86.0% | Win | Superseded · Hanzo-measured |
| Sep 28, 2026 | Kai a6 · a211cc70 | Accuracy | 94.0% | Jev 86.0% | Win | Superseded · Hanzo-measured |
| Sep 28, 2026 | Kai a8 · 0cfeef05 | Calibration error (ECE) | 0.024 | Jev 0.102 | Win | Superseded · Hanzo-measured |
| Sep 28, 2026 | Kai a7 · 0834a74f | Calibration error (ECE) | 0.034 | Jev 0.102 | Win | Superseded · Hanzo-measured |
| Sep 28, 2026 | Kai a6 · a211cc70 | Calibration error (ECE) | 0.028 | Jev 0.102 | Win | Superseded · Hanzo-measured |
| Sep 27, 2026 | Kai a5 · df1c16a2 | Accuracy | 95.0% | Jev 86.0% | Win | Superseded · Hanzo-measured |
| Sep 27, 2026 | Kai a5 · df1c16a2 | Calibration error (ECE) | 0.070 | Jev 0.102 | Win | Superseded · Hanzo-measured |
Conditions
- split: harness
- 400 questions, 400 answered
- dataset dde140a63fc5
- 6 Kai revisions measured
- Jev: typesafe/jev-1.13-20260917, measured Sep 25, 2026
Hardware
CPU AS SERVED
Reproduce
bench score --harness . --kai results/kai/preds.json.gz --out results/scores.json # in hanzoai/benchmarks/decision @ 5f616dd
