NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DA3TEETZZSB0AZM7P21FFK
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
6.0s
Cost:
$0.000515
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
13.53%
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 bell above the door of Hazel's Bakery jingled at half past six, and the cinnamon rolls were still too hot to frost. "You're early,"
the baker said
, not looking up from the proofing trays. "Couldn't sleep. Somebody's been in my shop." "Your shop? Since when do you own anything on Maple Street besides that rusty bicycle?" "Since the lease went through last week. Look at this." A small brass key lay on the counter, tied with a faded red ribbon. "That's the key to the old storeroom. Nobody's touched it since Mabel passed." "Exactly. And the lock's been pried. There are fresh scratches on the brass plate, and the dust on the shelves is smeared like someone crawled through." "Maybe Ed from the hardware store came by for the spare key." "Ed doesn't leave flour prints on the doorframe." A pause. The oven timer chimed, and neither of them moved to answer it. "Flour prints,"
the baker repeated slowly
. "How big?" "Small. Narrow heel. Like someone wearing your old clogs." "Those clogs have been in the donation box for a month." "Then someone's been pulling them out of that box, and they know this place better than we do." The baker wiped her hands on her apron, reached for the phone, and dialed a number she had known by heart for thirty years.
created_at
"2026-10-08T08:29:41.204Z"
10/8/2026, 8:29:41 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6016
moderation_latency
(null)
generation_time
6016
tokens_prompt
78
tokens_completion
325
native_tokens_prompt
109
native_tokens_completion
1009
native_tokens_completion_images
(null)
native_tokens_reasoning
558
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
0.0005154
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448181-scMRcHRnHW5uIvpDSi6u"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448181-UB7SrQKrlgSuGsPwuqzV"
upstream_id
"msg_011CfpTQpnLDYBsMHswr2Qvv"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTQpnLDYBsMHswr2Qvv"
is_byok
false
latency
690
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0005154
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
13.53%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"the baker said"
1
"the baker repeated slowly"