NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8WGZC4KS93TMC48WD7M7EV
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
10.3s
Cost:
$0.008920
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 morning rush had thinned to a trickle, leaving the bakery warm and quiet except for the hum of the ovens. Flour dusted the countertop where a tray of cinnamon rolls sat cooling, their glaze still catching the light from the front window. "You heard about the garden shed behind Margaret's place?" "Heard the sheriff's deputies were out there at dawn. Whole street was watching from their porches." "They found something buried. That's all anyone will say." "Margaret hasn't been herself since October. Stopped ordering her usual sourdough loaf. Switched to plain white. That alone should have raised flags." "You can't seriously judge a woman's innocence by her bread choices." "I'm just saying, people change their habits for reasons. And her reasons have been awfully mysterious." A timer chimed from the kitchen. The cinnamon rolls were nudged aside to make room for a fresh rack of scones, their edges golden and crumbling. "Her nephew was in here yesterday asking about Harold Finch. Whether I'd seen him lately." "Harold's been missing three weeks now." "Exactly." The front bell jingled. They both straightened, smiles sliding into place as the next customer stepped through the door.
created_at
"2026-02-24T22:32:41.613Z"
2/24/2026, 10:32:41 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1833
moderation_latency
283
generation_time
9993
tokens_prompt
81
tokens_completion
353
native_tokens_prompt
94
native_tokens_completion
338
native_tokens_completion_images
(null)
native_tokens_reasoning
33
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00892
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"bc21b1ef-0c95-4cd6-9430-1c4176d61f5d"
is_byok
false
latency
1804
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771972361-KijsgfsvyGySCzBAml2O"
upstream_id
"bc21b1ef-0c95-4cd6-9430-1c4176d61f5d"
total_cost
0.00892
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)