NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSJQT5153DB8W9TAG9JY081
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
9.0s
Cost:
$0.010985
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's first light spilled across the flour-dusted counter. "You're here early. Couldn't sleep either?" "How could I? After what happened to poor Mr. Abernathy last night, my mind's been racing like a runaway mixer." "Keep your voice down. The walls in this town have ears, and half of them are stopping by for cinnamon rolls in an hour." "I just can't believe it. He was sitting right there, in that corner booth, not three days ago. Ordered his usual." "The blueberry scone and black coffee. I remember. He left his newspaper folded to the crossword, like always." "Did the sheriff really question you?" "For an hour. Wanted to know who had access to the kitchen, who'd been hanging around. As if I'd know anything." "But you do know something, don't you? I can see it in your face." "...There was a receipt. Tucked inside his coat pocket when they found him. From this very bakery." "That's not unusual. He came in every day." "It was dated for tomorrow." "That's impossible." "Exactly. Someone printed it ahead of time. Someone who knew." A long silence stretched between them as the oven timer chimed. "We need to talk to the sheriff. Now."
created_at
"2026-05-29T09:58:37.995Z"
5/29/2026, 9:58:37 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
978
moderation_latency
(null)
generation_time
8961
tokens_prompt
81
tokens_completion
323
native_tokens_prompt
107
native_tokens_completion
418
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
0.010985
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_017esteUJXuH7kGD2rnRxxNh"
is_byok
false
latency
978
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-1780048717-BePTXuXxwnlKL7iIyya7"
session_id
(null)
api_type
"completions"
id
"gen-1780048717-wcMC19JulqgcrgPCMYCx"
upstream_id
"msg_017esteUJXuH7kGD2rnRxxNh"
total_cost
0.010985
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)