NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4D9YRBYS0JZ7JD00TZ7X1TS
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3.5s
Cost:
$0.000198
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
Messages
Meta
AI
Molly tapped the blueprint of the Henderson mansion. "The party starts at three. Every kid will be in the ballroom, and the presents sit in the east parlor." Bill squinted at the sketch, chewing a stale pretzel. "And the clown?" "Distraction. He does balloon animals every twenty minutes. Nobody watches the parlor during the swan." "What about the security guard?" "Uncle Ray is guarding the cake," Molly said. "Trust me, that's the most dangerous post in town." Bill grinned and pulled a fake mustache from his coat pocket. "I'll be the uncle who forgot the gift. Nobody questions a man with a sad, wrapped box." "You're bringing a box?" "Empty box. Very suspicious. Very heavy with guilt." Molly rolled her eyes, then slid a rolling duffel bag across the table. "Fine. Grab the wrapping paper. We're swapping the presents for the bags of marbles from the fridge." "Wait, why do they have marbles?" "Pinata prep," she said flatly. "Focus, Bill."
created_at
"2026-10-08T08:26:55.237Z"
10/8/2026, 8:26:55 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
789
moderation_latency
(null)
generation_time
3509
tokens_prompt
75
tokens_completion
245
native_tokens_prompt
95
native_tokens_completion
376
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"end_turn"
service_tier
"default"
usage
0.0001975
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448015-iKHwbeLiDCNZl6AIWPuY"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448015-QQvJIzCJ5r5bDoxdopgl"
upstream_id
"msg_011CfpTCbTojL2xXRzdAwkgt"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTCbTojL2xXRzdAwkgt"
is_byok
false
latency
789
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0001975
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Claude Platform on AWS"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
160
0.00%
Dialogue to Total Word Ratio
Ratio: 71.25%, Deviation: 61.25%
neededClean
false
wordsTotal
160
wordsDialogue
114
0.0000%