Skip to content
agent-swarm-optimization

claude-opus-5

agent-swarm-optimization — graded by the task's verifier against a measured baseline.

backend
modal
variant
claude claude-opus-5
metric
sealed AIME avg accuracy
actions
163
duration
5h 16m
recorded
2026-08-05

run idswarm-aime-optimization__kfV24B9

What the verifier emitted for this run, as recorded. The fields differ by task family — the task’s verification method explains what they mean.

metric
sealed AIME avg accuracy (%)
direction
higher_better
baseline
62.22
theoretical best
100
practical best
100
score
73.778
reward
0.817644
correctness
pass
accuracy pct
73.778
accuracy std over repeats
3.824
grade repeats
5
avg calls
2.986
avg completion tokens
27000.5
budget violations
1
efficiency multiplier
1.33958
reward before efficiency
0.610371
active llm nodes
3
meets node gate
pass
meets ceiling gate
pass
single node ceiling
62.22
bounty reached
fail
errors
none