NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-31-01KSYXB6AD79ZTENPN81FNWARC
Run Details
Model:
Claude Opus 4.8 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
9.9s
Cost:
$0.011285
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. Couldn't sleep either?" "Not after what happened to poor Mr. Abernathy. The whole town's talking about it." "Cinnamon roll? They're fresh. I find baking helps me think." "You always did. Remember when your mother ran this place? She'd say the same thing." "She'd also say I'm too nosy for my own good." "Well, you're not wrong to wonder. The man drops dead at the church social, and suddenly everyone's acting strange." "You noticed it too, then. The way Mrs. Pemberton wouldn't look anyone in the eye." "And the Henderson boy left before the ambulance even arrived." "That could mean anything. People panic." "Or people run when they've got something to hide." "You sound like one of those detective novels you're always reading." "Maybe. But I know what I saw. He drank that punch, made a face, and ten minutes later—" "Don't. Not before I've had my coffee." "I'm just saying, someone should ask questions. Quietly, of course." "Of course. Nothing draws attention like a baker asking about a dead man." "Exactly. Now hand me that frosting knife and tell me everything you remember about last night."
created_at
"2026-05-31T11:40:10.969Z"
5/31/2026, 11:40:10 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1288
moderation_latency
(null)
generation_time
9887
tokens_prompt
81
tokens_completion
330
native_tokens_prompt
107
native_tokens_completion
430
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
0.011285
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01RnQ5W9oF6mvipEMsqtDGAt"
is_byok
false
latency
1287
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-1780227610-wTx4KjmpgIr7ObH6c9sp"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780227610-4G7gZVF95lHrZzLid7TX"
upstream_id
"msg_01RnQ5W9oF6mvipEMsqtDGAt"
total_cost
0.011285
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)