NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DA2T42CWPNXC5HTZYPEK1N
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
5.9s
Cost:
$0.000523
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 up early,"
the baker said
, sliding a tray of cinnamon rolls onto the counter. "Didn't think anyone would be in before the sun." "Couldn't sleep. Not after what happened at the church bake sale." "Half the town is still whispering about it. Pie tins everywhere, and nobody saw a thing." "Somebody saw something. The lemon tart was fine when I dropped it off. By noon, it was poison." "Don't say that word in my shop. Customers are already nervous." "Then tell me why your flour bin smelled of almonds this morning." A long pause followed. The oven ticked as it cooled. "I was testing a new recipe. Almond extract, nothing more." "Almond extract doesn't come with a bitter edge. You know that as well as I do." "Keep your voice down. The Hendersons are in the back booth, and Margaret never misses a word." "Then let's talk somewhere she can't hear. Who else had access to the church kitchen that morning?" "Everyone who ever volunteered. Including you." "Exactly. Which is why I'm asking you first." "Fine. But if you're going to play detective, you'd better eat something. Detectives who skip breakfast make terrible decisions." "Then give me the cinnamon roll, and tell me the truth while I eat it."
created_at
"2026-10-08T08:29:08.105Z"
10/8/2026, 8:29:08 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5850
moderation_latency
(null)
generation_time
5850
tokens_prompt
78
tokens_completion
313
native_tokens_prompt
109
native_tokens_completion
1025
native_tokens_completion_images
(null)
native_tokens_reasoning
584
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
0.0005234
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448148-mfX0GjQCy39Rzz2V214M"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448148-mE5wt0yG1JqVbBN1i6Lv"
upstream_id
"msg_011CfpTNPL5tb8AGMG2jePfx"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTNPL5tb8AGMG2jePfx"
is_byok
false
latency
685
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0005234
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
"the baker said"