NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DYHCJEAHBJTVQ7SHG8HGGV
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
2m 5s
Cost:
$0.014487
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
100.00%
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
The bakery's ovens were still ticking as they cooled, and the back kitchen smelled of cinnamon and scorched sugar. "You're in early. Couldn't sleep?" "Somebody was in here last night." "Don't be ridiculous. I locked up myself." "Then explain the window over the sink. It's cracked open, and there are heel prints in the mud beneath it." "Heels? Nobody in this town wears heels before nine." "One person does, and she bathes in that gardenia perfume." "Vivian Thorne would sooner die than climb through a window. She'd use the front door and complain about the draft." "Then look at the cinnamon tin. It's empty, and someone tied a blue ribbon around it." "Blue, like the first prize at the Harvest Fair. The judges taste our pies at ten tomorrow, and she knows it. Oh, that woman." "Wait. Nobody leaves a calling card that obvious unless they want us to blame her." "Then someone's trying to make us look the wrong way, and I'd like to know who." "Which means someone's been watching us bake for weeks, long enough to know exactly where we keep the cinnamon." Across Main Street, a car idled at the curb with its headlights off.
created_at
"2026-10-08T14:26:37.278Z"
10/8/2026, 2:26:37 PM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2384
moderation_latency
(null)
generation_time
125204
tokens_prompt
78
tokens_completion
4539
native_tokens_prompt
109
native_tokens_completion
28952
native_tokens_completion_images
(null)
native_tokens_reasoning
28537
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
0.0144869
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791469597-mqi8g1OmnYG7mK7VwNCu"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791469597-L1k4rYs7Ic5G04Ne18Uc"
upstream_id
"msg_011CfpvdW8BJUDmVVofd11Jj"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpvdW8BJUDmVVofd11Jj"
is_byok
false
latency
813
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0144869
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
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)