NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DA41B69EA5SVCTHK0BHEW9
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.9s
Cost:
$0.000186
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
82.08%
Dialogue to Total Word Ratio
(details)
41.0377%
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
Messages
Meta
AI
"Right, the plan's simple," Molly whispered, tapping the blueprint. "We slip in through the bouncy castle vent." "Bouncy castle vent? Molly, that's a kid's castle in the back garden." "Exactly. Nobody checks a bouncy castle for criminals." "Fine. Then what?" "Then we wait for the clown to finish the balloon animals. Once he's distracted, we grab the presents from under the tree." "What if the clown spots us?" "Bill, he's been doing balloon swords all afternoon. He can't spot a sandwich." "Okay, but what about the kid with the cardboard crown? He's been staring at us since we arrived." "Ignore him. He's six." "He's six and he's holding a water pistol, Molly." "Then we use the bouncy castle as cover. Quiet, now. The parents are bringing out the cake." "Cake is a distraction. I'm going for the cake." "You're going for the presents, Bill. Stay focused." "Right. Presents. Got it."
created_at
"2026-10-08T08:29:48.27Z"
10/8/2026, 8:29:48 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
697
moderation_latency
(null)
generation_time
2876
tokens_prompt
75
tokens_completion
232
native_tokens_prompt
95
native_tokens_completion
352
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
0.0001855
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448188-X28Bdz2iDDWgsHphq2m7"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448188-kdRdnxNYmiL48yzwHDRl"
upstream_id
"msg_011CfpTRMEuUAuD4nrrEQnYk"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTRMEuUAuD4nrrEQnYk"
is_byok
false
latency
697
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0001855
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
150
82.08%
Dialogue to Total Word Ratio
Ratio: 96.67%, Deviation: 6.67%
neededClean
false
wordsTotal
150
wordsDialogue
145
41.0377%