NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1GV7C5PS6TV6A7SQAVCPZQ
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
9.5s
Cost:
$0.010560
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 cinnamon rolls aren't even out yet." "I'm not here for the rolls, Margaret. I'm here about Edith." "What about her? She was just in yesterday, fussing over the lemon tarts like always." "That's just it. She never made it home." The sound of a tray clattering against the counter filled the silence. "You can't be serious. Edith's lived on Maple Street for forty years. She could walk that route blindfolded." "Her sister called me this morning. The bed wasn't slept in. No note, nothing." "And you came to the bakery first? Shouldn't you be out looking?" "I am looking. You're the last person who saw her, near as I can tell. Did she say anything strange? Anything at all?" A long pause, broken only by the ticking of the wall clock. "Now that you mention it... she did seem distracted. Kept glancing out the window like she was waiting for someone. Wouldn't touch her tea." "Did you see who?" "No. But when she left, she didn't take her usual bag of day-olds. First time in years." "Margaret, I think we'd better sit down."
created_at
"2026-06-01T11:59:28.139Z"
6/1/2026, 11:59:28 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1175
moderation_latency
(null)
generation_time
9428
tokens_prompt
81
tokens_completion
308
native_tokens_prompt
107
native_tokens_completion
401
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
0.01056
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01YBkkMwDhcSut8WNJgk8ynF"
is_byok
false
latency
1175
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-1780315168-8dgnCwN59hIB93cUJkU0"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780315168-Euhv1PqCtFEME6brWFOo"
upstream_id
"msg_01YBkkMwDhcSut8WNJgk8ynF"
total_cost
0.01056
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)