Run: 2026-02-24-01KJ8WBB4VTJ3WR73CDJ5XPC2P

Run Details

Duration:
11.7s
Cost:
$0.010135
Provider:
Amazon Bedrock

Evaluation summary

Score Evaluator
Details Link
99.92% Matches word count (details)
97.37% Dialogue to Total Word Ratio (details)
98.6446% Overall

Model input

User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Molly spread the hand-drawn map across the hood of their dented minivan. Crayon smudges marked the entry points. Bill squinted at it, holding his reading glasses with one hand and a juice box with the other. "The bouncy castle goes up at noon," Molly said, tapping a purple blob on the map. "That's our distraction window." "What about the mother?" Bill asked. "She looks like she does CrossFit." "Karen will be busy refilling the lemonade station. I timed her last Saturday during the rehearsal party." Molly cracked her knuckles with theatrical menace. "We go in through the garage, grab the gift table, and load everything into the van before the piƱata drops." Bill sucked the last of his juice box dry with a long, sad gurgle. He studied the map again, rotating it twice before realizing he had been holding it upside down. "What if a kid sees us?" "Kids love strangers carrying large bags. We tell them we're Santa's helpers." "It's July, Molly." "Kids are stupid, Bill." He considered this with the gravity of a man who had once been outsmarted by a revolving door. Finally, he nodded. "I'll wear the elf shoes." "That's the spirit."
created_at"2026-02-24T22:29:37.059Z" 2/24/2026, 10:29:37 PM
model"anthropic/claude-4.6-opus-20260205"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1519
moderation_latency172
generation_time11466
tokens_prompt77
tokens_completion376
native_tokens_prompt92
native_tokens_completion387
native_tokens_completion_images(null)
native_tokens_reasoning69
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"
usage0.010135
router(null)
provider_responses
0
endpoint_id"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id"df7b7325-cd31-4aee-9a83-4f4309e879a1"
is_byokfalse
latency1488
model_permaslug"anthropic/claude-4.6-opus-20260205"
provider_name"Amazon Bedrock"
status200
api_type"completions"
id"gen-1771972177-RMF7wmF6hAQMovgiYNXJ"
upstream_id"df7b7325-cd31-4aee-9a83-4f4309e879a1"
total_cost0.010135
cache_discount(null)
upstream_inference_cost0
provider_name"Amazon Bedrock"

Evaluation details

Result Evaluator Details Meta Data
99.92% Matches word count n/a
neededCleanfalse
words197
97.37% Dialogue to Total Word Ratio
Ratio: 45.96%, Deviation: 4.04%
neededCleanfalse
wordsTotal198
wordsDialogue91
98.6446%