NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCR2T6B6VSAJ1EJ1A74VR2G
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
11.6s
Cost:
$0.014590
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
0.30%
Dialogue to Total Word Ratio
(details)
49.8364%
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 unrolled the blueprint across the hood of the van. It was a paper placemat from the pizza parlor, but it had a maze on it, and she felt that counted. "Bouncy castle here," she said, tapping a grease stain. "PiƱata here. Presents stacked on the folding table, northeast corner, guarded by grandmothers." "How many grandmothers?" "Four. Possibly five. One of them knits, so assume she's armed." Bill chewed his thumbnail. "And we just walk in?" "We walk in as entertainment. You're the clown." "Why am I always the clown?" "Because you have the face for it, Bill, and I mean that with love." Molly handed him a red foam nose that had clearly been chewed by something. "I'll be the magician. Magicians get a table, a cloth, and nobody questions a large black bag." "What about the birthday boy?" "Theodore. Turns seven at three-fifteen. He's allergic to strawberries, afraid of mimes, and has a metal detector on his wish list, which I find personally insulting." Bill squeezed the nose onto his face and exhaled through his mouth. "This feels wrong." "It's a *heist*, Bill. Wrong is the genre." "No, I mean the nose. It's damp." Molly folded the placemat. "Then wear it proudly. Showtime."
created_at
"2026-07-25T13:40:22.866Z"
7/25/2026, 1:40:22 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5153
moderation_latency
(null)
generation_time
11460
tokens_prompt
75
tokens_completion
357
native_tokens_prompt
93
native_tokens_completion
565
native_tokens_completion_images
(null)
native_tokens_reasoning
48
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
0.01459
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsSL5jrs1R1JhyDbYXD"
is_byok
false
latency
2686
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-1784986822-TfLugRWPmkjlLeb2gFJL"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986822-h6xOX5L9G1aKnmUMS1Aq"
upstream_id
"msg_011CdNsSL5jrs1R1JhyDbYXD"
total_cost
0.01459
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
99.38%
Matches word count
n/a
neededClean
false
words
205
0.30%
Dialogue to Total Word Ratio
Ratio: 65.53%, Deviation: 15.53%
neededClean
false
wordsTotal
206
wordsDialogue
135
49.8364%