NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1GRFVYKX365MZE6EKSXCB9
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
9.0s
Cost:
$0.010610
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 the morning light spilled across the worn wooden floor. "You're here early. Couldn't sleep either?" "Not after what happened to poor Mr. Abernathy. Right here in town, can you believe it?" "I heard he was found in his study. Such a shame, he always bought the cinnamon rolls on Sundays." "Two of them. Never just one." A pause, the soft scrape of a tray being set down. "Did the police say anything?" "Only that it wasn't an accident. The way Officer Combs was asking questions, you'd think half of us were suspects." "Well, somebody knew something. He wasn't the type to make enemies." "Everyone makes enemies, dear. Some just hide them better than others." The clink of a coffee cup against a saucer. "You don't think it was anyone we know, do you?" "I try not to think such things before my second cup. But I'll tell you what's strange—he came in Thursday looking pale as flour. Asked me if I could keep a secret." "And did you?" "He never told me what it was. Left without his rolls, which he'd never done before." "Never?" "Not once in twelve years. That's when I knew something was terribly wrong."
created_at
"2026-06-01T11:57:58.53Z"
6/1/2026, 11:57:58 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1170
moderation_latency
(null)
generation_time
8975
tokens_prompt
81
tokens_completion
310
native_tokens_prompt
107
native_tokens_completion
403
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
0.01061
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_019P6biu2hVymcnHauiwYGhz"
is_byok
false
latency
1170
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-1780315078-jJJ1BZK56nd6HGAkp2jG"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780315078-dCDq67YrFN6yY6S47v6e"
upstream_id
"msg_019P6biu2hVymcnHauiwYGhz"
total_cost
0.01061
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)