NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCQVYE8F1GX385560AME7D5
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.1s
Cost:
$0.012290
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
98.09%
Dialogue to Total Word Ratio
(details)
99.0380%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
"Bouncy castle," Molly said. "That's our way in." "That's not a way in. That's a way to sprain an ankle." "It abuts the fence, Bill. We go over, we land soft, we're inside the perimeter dressed as clowns." "I'm not being a clown." "You're already a clown." "I'm not being a *professional* clown, Molly. There's a difference. Clowns get hugged. Clowns get asked to make balloon giraffes." "Can you make a balloon giraffe?" "I can make a balloon sausage." "Then you're a novice clown, and nobody expects much. Now. Presents are stacked on the folding table, left of the piñata. Forty minutes into the party, they light the candles, the lights go down—" "It's two in the afternoon." "—the *mood* goes down, everyone sings, and that's ninety seconds where thirty adults are staring at a cake. We load the presents into the bin bags." "And the getaway?" "Ice cream van." "We don't have an ice cream van." "We have a van, and I have a speaker that plays 'Greensleeves.'" "Children will chase us." "Children always chase us, Bill. That's the job." "What if there's a magician?" "Then we're professionals, and we watch the trick, and *then* we steal from a seven-year-old."
created_at
"2026-07-25T13:36:37.84Z"
7/25/2026, 1:36:37 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2532
moderation_latency
(null)
generation_time
8947
tokens_prompt
75
tokens_completion
327
native_tokens_prompt
93
native_tokens_completion
473
native_tokens_completion_images
(null)
native_tokens_reasoning
20
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
0.01229
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNs9jEoQua9AuvwYy49u"
is_byok
false
latency
1412
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-1784986597-B6TqQgsXljUVV8xylpiE"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986597-hAdL3R83p1idyly6N8z7"
upstream_id
"msg_011CdNs9jEoQua9AuvwYy49u"
total_cost
0.01229
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
99.98%
Matches word count
n/a
neededClean
false
words
202
98.09%
Dialogue to Total Word Ratio
Ratio: 86.27%, Deviation: 3.73%
neededClean
false
wordsTotal
204
wordsDialogue
176
99.0380%