NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRPD91KWV8PQFVTMPFSVEQ
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.3s
Cost:
$0.013115
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
99.63%
Dialogue to Total Word Ratio
(details)
99.7761%
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's the weak point," Bill said. "It's a children's party, Bill. There is no weak point. It's all weak point." "Then why've I been up three nights with the blueprints?" "You drew those blueprints. On a napkin. From memory." "From reconnaissance." "You stood outside a semi-detached in Croydon eating a Twix." "Deep cover." Bill tapped the napkin. "Present pile's here, by the piñata. Fourteen gift bags, one big box — bike, I reckon — and something wrapped in that paper with the dinosaurs, which is the good stuff, Molly. Nobody wraps rubbish in dinosaurs." "And the forty children?" "Distraction. That's your bit." "My bit." "You do the magic show. Balloon animals. Little bow." "I don't do balloon animals." "You did that swan at Christmas." "That was a swan-shaped grievance and you know it." Molly sighed. "What about the parents? Mums see everything. Mums have got, like, radar." "That's why we go in at cake time. Candles out, lights low, everyone singing. Thirty seconds of pure chaos." "And we walk out with a bike." "We walk out with a bike." "Bill." Molly folded the napkin carefully. "Whose birthday is it?" A pause. "...My nephew's." "Right. I'm doing the swan."
created_at
"2026-07-25T13:51:05Z"
7/25/2026, 1:51:05 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2433
moderation_latency
(null)
generation_time
10178
tokens_prompt
75
tokens_completion
349
native_tokens_prompt
93
native_tokens_completion
506
native_tokens_completion_images
(null)
native_tokens_reasoning
35
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
0.013115
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNtFepg5dw3peuqZk1zq"
is_byok
false
latency
1275
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-1784987465-1i43kLawy46yphLBjZQx"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987465-5Ad6UW28gsktlcIdR6p1"
upstream_id
"msg_011CdNtFepg5dw3peuqZk1zq"
total_cost
0.013115
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
99.92%
Matches word count
n/a
neededClean
false
words
197
99.63%
Dialogue to Total Word Ratio
Ratio: 92.46%, Deviation: 2.46%
neededClean
false
wordsTotal
199
wordsDialogue
184
99.7761%