Your benchmark score is a harness scoreGLM-5.3-Flash · Terminal-Bench 2.1 · one model, many harnesses

0 / 0 trials
0 running · 0 people contributing

Workshop leaderboard · Ref = Harness Leaderboard

HarnessPass rate95% CIRefTrials$ / trial

Cost vs pass rate

workshop runs (≥ 5 trials)Harness Leaderboard (ref)

Grid · openrunningpassfail

Newest results