NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCQQNMSGGESFPSKW81421RM
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
16.2s
Cost:
$0.026665
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
27.17%
Matches word count
(details)
0.02%
Dialogue to Total Word Ratio
(details)
13.5923%
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 smoothed a napkin across the sticky café table and drew a lopsided rectangle with a stolen pen. "Bouncy castle. Cake table. Presents, stacked here." "How many presents?" Bill asked, chewing his straw flat. "Forty. Maybe fifty. The boy's turning seven and his father owns three car dealerships." "So the loot is Lego." "The loot is unopened, boxed, gift-receipted Lego. Do you know what that fetches online?" "I know what a seven-year-old sounds like when he cries." "Then wear the earplugs." She tapped the napkin twice. "You go in as the clown." Bill set down his straw with the solemnity of a man laying a wreath. "Absolutely not." "You own the shoes." "I own those shoes because of an unrelated incident, and you know it." "Twenty minutes of balloon animals, then you lead the parents out to the piñata while I load the van." "I can only make a snake." "Call it an eel. Children can't tell the difference." Molly slid a red foam nose across the table, past the ketchup. "Two o'clock sharp. There's a photographer, so chin down, wig straight." Bill turned the nose over in his enormous hands, examining it like a live grenade. "And if a child requests a giraffe?" "Then you hand them a snake," she said, standing, "and you tell them it's abstract."
created_at
"2026-07-25T13:34:17.761Z"
7/25/2026, 1:34:17 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4350
moderation_latency
(null)
generation_time
16065
tokens_prompt
75
tokens_completion
408
native_tokens_prompt
93
native_tokens_completion
1048
native_tokens_completion_images
(null)
native_tokens_reasoning
80
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
0.026665
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNryQww7ATfhus2PsNEB"
is_byok
false
latency
1801
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-1784986457-FP2t8mPJdV8L7v5jtpVO"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986457-vnq6zMOC3Zx2AnLofuf3"
upstream_id
"msg_011CdNryQww7ATfhus2PsNEB"
total_cost
0.026665
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
27.17%
Matches word count
n/a
neededClean
false
words
219
0.02%
Dialogue to Total Word Ratio
Ratio: 67.12%, Deviation: 17.12%
neededClean
false
wordsTotal
222
wordsDialogue
149
13.5923%