NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPVRHRH7AZR765MYPHNZP0
Run Details
Model:
Claude Opus 5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
11.2s
Cost:
$0.012690
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
18.99%
Dialogue to Total Word Ratio
(details)
59.3689%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Molly spread the crayon-drawn map across the hood of the van. "The bouncy castle's here," she said, tapping a lopsided blue blob. "Cake table, here. Presents, stacked by the piñata." "How many kids?" Bill asked. "Twenty-two. Plus mothers." "Mothers." Bill exhaled through his teeth. "Mothers are worse than dogs, Moll. Dogs you can bribe." "Which is why you're going in as the clown." "Absolutely not." "You've got the shoes." "I have the shoes because of an unrelated incident." Molly ignored him and drew a red arrow across the patio. "You do balloon animals for eleven minutes. Long enough for me to walk out the side gate with the loot bag." "And when the birthday boy wants a giraffe?" "Give him a snake. Nobody can tell." Bill studied the map, scratching his jaw. A distant, terrible sound of children reached them from over the fence — shrieking, joyous, feral. "There's no honor in this," he said quietly. "There's a PlayStation in there, Bill. Two of them. Rich kid, divorced parents, competitive gift-giving." He was silent for a long moment. "Fine. But I'm keeping the tricycle." "Deal." "And if anyone cries," Bill said, tugging on the red nose, "we abort." Molly patted his cheek. "You sentimental fool."
created_at
"2026-07-25T13:19:03.231Z"
7/25/2026, 1:19:03 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1965
moderation_latency
(null)
generation_time
11096
tokens_prompt
75
tokens_completion
320
native_tokens_prompt
93
native_tokens_completion
489
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
0.01269
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqp1TgvVGJ7F9SPydLw"
is_byok
false
latency
1962
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-1784985543-KujibThl1Bdj96gkezbX"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985543-wBV2CsUFK21gHWNTSK9h"
upstream_id
"msg_011CdNqp1TgvVGJ7F9SPydLw"
total_cost
0.01269
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
99.74%
Matches word count
n/a
neededClean
false
words
204
18.99%
Dialogue to Total Word Ratio
Ratio: 61.35%, Deviation: 11.35%
neededClean
false
wordsTotal
207
wordsDialogue
127
59.3689%