NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSJMFEVZMEXQ98EHVX167W1
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
10.5s
Cost:
$0.011160
Provider:
Anthropic
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 bell above the door jingled as warm air rushed out to greet the morning chill. "You're here early. The croissants aren't even out of the oven yet." "I couldn't sleep. Not after what happened to poor Mr. Abernathy." "Terrible business, that. Found him right there in his garden, they say." "You don't think it was natural causes, do you? A man his age, working in the heat?" "He was seventy-three and fit as a fiddle. Walked past this window every morning at seven sharp for the past decade." "Then who would want to harm him? Everyone loved Harold." "Not everyone. You didn't hear the row he had with his nephew last Tuesday. Right out on the sidewalk, shouting about the will." "The will? I thought the boy was getting everything anyway." "That's just it. Harold told me—right where you're standing—that he'd changed his mind. Going to leave the house to the historical society instead." "You don't say." "I do say. And I'd wager that nephew knew about it too." "Should we tell the sheriff?" "After breakfast. No sense gossiping on an empty stomach. Now, are those almond ones ready yet?" "Two minutes. And not a word to anyone until we're certain." "My lips are sealed. Mostly."
created_at
"2026-05-29T09:56:48.741Z"
5/29/2026, 9:56:48 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1936
moderation_latency
115
generation_time
10358
tokens_prompt
81
tokens_completion
324
native_tokens_prompt
107
native_tokens_completion
425
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
0.01116
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_019xz9YNTP1hn5qe9gCwZTHw"
is_byok
false
latency
1936
model_permaslug
"anthropic/claude-4.8-opus-20260528"
provider_name
"Anthropic"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.16.0; linux; x64))"
http_referer
(null)
request_id
"req-1780048608-EhTj7xuxIV1Bd89Zrefa"
session_id
(null)
api_type
"completions"
id
"gen-1780048608-8obB9DWOrawIV34sUftr"
upstream_id
"msg_019xz9YNTP1hn5qe9gCwZTHw"
total_cost
0.01116
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)