The public run log
Published Results
One harness. One model. One challenge. Inspect what changed when a Skill changed. Newest submissions first, not ranked by score.
Only Climb runs can be published today. A test of your own Skill stays on your computer; the tdd example shows what one looks like.
02 Model
03 Challenge
04 Ran on
Showing 5 of 5 Results Signed by the publisher · Files checked · Not rerun by anyone else
Scores are each run's mean task score over its tasks, rounded to three decimal places. Each Climb's page says how its tasks are scored.
| Skill comparison | Baseline | Candidate | Change | Tasks ↑ / = / ↓ | Verdict | Ran on | Published | Evidence |
|---|---|---|---|---|---|---|---|---|
| tasksmith-starter-v1 vs baseline Name given by the publisher; not checked HF Tasksmith · Hermes v2026.9.24 · openai/gpt-6-luna | 0 | 0.333 | +0.333 | 2 / 4 / 0 | Too close to call 1 run | Own Prime key | Inspect → | |
| frontier-cs-v2 vs baseline Name given by the publisher; not checked Frontier-CS Open-Ended · Hermes v2026.7.20 · qwen/qwen3.7-flash | 0.131 | 0.1 | -0.031 | 2 / 5 / 3 | Too close to call 1 run | Own Prime key | Inspect → | |
| frontier-cs-v1 vs baseline Name given by the publisher; not checked Frontier-CS Open-Ended · Hermes v2026.7.20 · qwen/qwen3.7-flash | 0.128 | 0.043 | -0.085 | 1 / 6 / 3 | Too close to call 1 run | Own Prime key | Inspect → | |
| hello-world-v1 vs baseline Name given by the publisher; not checked Techtree Hello World · Hermes 0.19.0 · qwen/qwen3.7-flash | 0 | 0.611 | +0.611 | 22 / 14 / 0 | Improved 1 run | Own Prime key | Inspect → | |
| hello-world-v1 vs baseline Name given by the publisher; not checked Techtree Hello World · Hermes 0.19.0 · qwen/qwen3.7-flash | 0 | 0.667 | +0.667 | 24 / 12 / 0 | Improved 1 run | Own Prime key | Inspect → |
The first entries are Techtree’s own release-check Results. They use the same format, checks, and ordering as every other published Result.