NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCQWRR8JA2Y9NJ7W2H2B1BM
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
12.4s
Cost:
$0.012535
Provider:
Amazon Bedrock
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 over the door gave its usual tired jangle, and the smell of cardamom buns rolled out to meet the cold. "You're early. I haven't even glazed the crullers." "I didn't come for crullers. I came because Marjorie Pike's kitchen light was on at four this morning, and Marjorie Pike hasn't risen before nine since her hip went." "So she couldn't sleep." "So she was baking. And this afternoon there'll be a lemon drizzle at the church sale with her name on the card, and everyone will coo over it, and I will know." A pause, filled with the scrape of a spatula across a cooling rack. "You think she's using my recipe." "I think she's using your recipe, your tin, and the oven thermometer that went missing off your windowsill in September." "That's a serious accusation to make before six." "I've made worse before five." Flour drifted through the lamplight, settling on the counter like fine snow. "Sit down. Have a bun. If she has got the recipe, she'll have got it wrong — she never could resist adding almond." "And if she hasn't got it wrong?" "Then, Enid, we shall have to find out who did give it to her. And I'll want a very large pot of tea first."
created_at
"2026-07-25T13:37:04.784Z"
7/25/2026, 1:37:04 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3903
moderation_latency
(null)
generation_time
12319
tokens_prompt
78
tokens_completion
376
native_tokens_prompt
107
native_tokens_completion
480
native_tokens_completion_images
(null)
native_tokens_reasoning
75
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
0.012535
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsBi69g4pThUwmVGv6o"
is_byok
false
latency
1795
model_permaslug
"anthropic/claude-opus-5-20260723"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784986624-oCPPseMMpQhYmcAceYdI"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986624-frJF928TBKGVs4uofkVq"
upstream_id
"msg_011CdNsBi69g4pThUwmVGv6o"
total_cost
0.012535
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)