NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DA5EP7B16TPJHGXJ66CHQN
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
3.8s
Cost:
$0.000208
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
60.65%
Count dialogue tags
(details)
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
"You're late,"
Marigold said
, not looking up from the tray of cinnamon rolls. "The bridge was up again. Something about a barge." Teddy set his umbrella in the corner, where it dripped onto the mat. "Is that the good icing?" "Is there any other kind?" "Ha. Careful, you'll make me think you're in a good mood." "I'm always in a good mood before nine." "Then why does the lock on the back door look scratched?" A pause. The oven ticked as it cooled. "Probably the delivery boys. They're careless." "Mm. Delivery boys don't leave wax drippings on the windowsill." "Teddy." "I'm only saying. Somebody lit a candle back here last night, and somebody else has been very quiet about it." "Fine. I was up late. The ledger didn't balance." "Ah. And the ledger is why Hollis came in yesterday, asking for the Thursday receipts?" Marigold set down her piping bag. "Hand me the flour, would you? And keep your voice down. The walls in this place have ears, and most of them belong to Mrs. Peabody." "Then let's talk about what's really in that safe."
created_at
"2026-10-08T08:30:34.703Z"
10/8/2026, 8:30:34 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3725
moderation_latency
(null)
generation_time
3725
tokens_prompt
78
tokens_completion
271
native_tokens_prompt
109
native_tokens_completion
394
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
0.0002079
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448234-HtU0pc4WhVcf6VIMWnfW"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448234-mdeHSgjZXaahIQ6y6dQc"
upstream_id
"msg_011CfpTUmpbZvnRe4sJgMSRq"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTUmpbZvnRe4sJgMSRq"
is_byok
false
latency
735
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0002079
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
60.65%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"Marigold said"