Run: 2026-02-24-01KJ8V95ZK69SBTDAV7PAPW4E7

Run Details

Duration:
10.0s
Cost:
$0.010285
Provider:
Amazon Bedrock

Evaluation summary

Score Evaluator
Details Link
75.16% Matches word count (details)
99.91% Dialogue to Total Word Ratio (details)
87.5351% Overall

Model input

User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.

Model response

AI
"Alright, Bill, run me through it one more time," Molly said, spreading the hand-drawn map across the dashboard. "We go in through the back gate at fourteen hundred hours. The bouncy castle provides cover on the left flank. I neutralize the piƱata as a distraction while you grab the presents off the fold-out table." "And the parents?" "Intel says they'll be in the kitchen doing Jell-O shots by two fifteen. We'll have a clean four-minute window." "What about the birthday boy?" "He's six, Molly. I think we can handle a six-year-old." "You said that about the Hendersons' kid last Easter and you still have the bite marks." "That was different. That kid was feral. This one does watercolors." "Fine. What's our exit strategy?" "Over the fence, through Mrs. Patterson's garden, into the getaway minivan. I've got car seats installed so we blend in with the neighborhood." "Brilliant. And the loot?" "Conservative estimate, we're looking at eight to ten wrapped presents. Probably some Legos, maybe a scooter. Could be our biggest haul since the Petersons' baby shower." Molly folded the map and grinned. "Let's go rob some children."
created_at"2026-02-24T22:10:57.659Z" 2/24/2026, 10:10:57 PM
model"anthropic/claude-4.6-opus-20260205"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1296
moderation_latency162
generation_time9797
tokens_prompt77
tokens_completion380
native_tokens_prompt92
native_tokens_completion393
native_tokens_completion_images(null)
native_tokens_reasoning72
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.010285
router(null)
provider_responses
0
endpoint_id"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id"ee6c03a7-685d-4c1e-98a4-fcb580c472e8"
is_byokfalse
latency1260
model_permaslug"anthropic/claude-4.6-opus-20260205"
provider_name"Amazon Bedrock"
status200
api_type"completions"
id"gen-1771971057-O0QrtHxNxm0BS2l3j0eI"
upstream_id"ee6c03a7-685d-4c1e-98a4-fcb580c472e8"
total_cost0.010285
cache_discount(null)
upstream_inference_cost0
provider_name"Amazon Bedrock"

Evaluation details

Result Evaluator Details Meta Data
75.16% Matches word count n/a
neededCleanfalse
words187
99.91% Dialogue to Total Word Ratio
Ratio: 91.71%, Deviation: 1.71%
neededCleanfalse
wordsTotal193
wordsDialogue177
87.5351%