NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DAH4F3HX41AK2THN5HRXHX
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
3.6s
Cost:
$0.000199
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,"
Maggie said
, not looking up from the tray of cinnamon rolls she was glazing. "The bakery was closed when I got here. Door was unlocked, though." "I always leave it unlocked for the delivery boy. He never shows." "Someone's been in the back. The flour sack's split open, and there's a footprint on the floor." "Probably Edna. She's been sneaking in for her morning scone since her husband passed. Doesn't like to be seen." "Edna doesn't wear size-eleven boots." A pause. The oven ticked as it cooled. "Then who has been using my ovens at four in the morning?" "That's what I intend to find out. Hand me that pastry brush." "Before you start playing detective, you should know the back window's broken too." "Of course it is. Everything in this town waits until I'm busy to fall apart." "There's something else. Behind the proofing cabinet. A ledger, with your name crossed out and someone else's written in." Silence. The glaze dripped slowly onto the marble. "Well," Maggie finally said, "now I'm glad I didn't sleep last night."
created_at
"2026-10-08T08:36:57.452Z"
10/8/2026, 8:36:57 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3538
moderation_latency
(null)
generation_time
3538
tokens_prompt
78
tokens_completion
271
native_tokens_prompt
109
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
0.0001989
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448617-s8Z50GjcVWu6zUwhVOYK"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448617-691u3Q9nIuvqDjqpEfer"
upstream_id
"msg_011CfpTxz93iHy41Ckx7Y4XR"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTxz93iHy41Ckx7Y4XR"
is_byok
false
latency
796
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0001989
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
"Maggie said"