NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-31-01KSYXKABXNZ08C5K1J4KJ31F6
Run Details
Model:
Claude Opus 4.8 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
8.9s
Cost:
$0.010810
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 she stepped inside, the warm scent of cinnamon wrapping around her like a hug. "You're late. The scones are nearly gone." "I had a good reason this time, I promise." "You always have a good reason. Last week it was a flat tire. The week before, a lost cat." "This one's better. You'll never guess what I found behind the old Hargrove place." "If you say another stray cat, I'm cutting you off from the lemon tarts." "A locked box. Buried under the rose bushes, just like Mrs. Pemberton said." The clatter of a dropped tray broke the quiet. "You're joking. You actually went looking?" "Of course I did. You don't drop a hint like that and expect me to ignore it." "And? What was inside?" "That's the thing. I couldn't open it. The lock's rusted solid, and there's an initial carved into the lid. A letter 'H,' I think." "Hargrove." "Or Hadley. Or Hutchins. Half this town starts with an H." A long pause, then the soft scrape of a chair being pulled out. "Sit down. Pour yourself some coffee. We're going to figure this out properly—and this time, I'm coming with you."
created_at
"2026-05-31T11:44:37.26Z"
5/31/2026, 11:44:37 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1132
moderation_latency
(null)
generation_time
8818
tokens_prompt
81
tokens_completion
303
native_tokens_prompt
107
native_tokens_completion
411
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
0.01081
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01F6aVH9CAyTyJQFWDStm7QX"
is_byok
false
latency
1132
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-1780227877-TTQmhfO9uaRcZtX2Oj5D"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780227877-noUfmGNnEzyubuwH5ywT"
upstream_id
"msg_01F6aVH9CAyTyJQFWDStm7QX"
total_cost
0.01081
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)