AI Model Reviewer

Hermes Agent 0.21.5

1 model ran in it: Claude Opus 5.5.

10 runs on 7 prompts · 10% finished

Results

The best run of each of its 7 tests first, then every other run. Filter them in the explorer

1 finished runs

  • Claude Opus 5.5, Hermes Agent: California brown pelican riding a bicycle (detailed spec)

    California brown pelican riding a bicycle (detailed spec)

    Claude Opus 5.5

    Hermes Agent 0.21.5

    skills off

Numbers: finish rate, cost, wall time, draft scores
Runs
10
on 7 prompts
Finished
10%
1 of 10
Median cost, finished run
$23.83
n=1
Median wall time, finished run
2h 30m
n=1
Recorded spend
$50.71
$26.88 on unfinished runs; 8 without a recorded cost

From the numbers

Set against the other harnesses with at least 3 runs (top or bottom third), and its draft-score ranks within single prompts. Nothing here is averaged across prompts.

Strengths

  • Nothing stands out with enough runs to say so.

Weaknesses

  • 1 of 10 runs finished: 13th of 14 harnesses with at least 3 (finish rate)
  • 1 run ended as the model's own failure (DNF, class MODEL)
  • Other unfinished runs, not counted against the model: 1 INFRA, 7 TIMEOUT

Best and hardest run

Best run

Picked as its fastest finished run (no scored result yet).

Hardest run

Picked as its costliest run that did not finish.

Draft scores by prompt

No scored result yet (only prompts with a published rubric are scored).

By model

Claude Opus 5.510110%$23.83 n=12h 30m n=1
All 7 tests