NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0GG25HXQBCCHTG4TEGWVPG
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
6.9s
Cost:
$0.012590
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
75.9606%
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
Molly unrolled a crayon-scribbled map across the table. "Okay, Bill. Bouncy castle's here, piƱata's there, and the loot pile is under the unicorn banner." "Unicorn banner. Got it." Bill squinted. "What's our window?" "Pin the Tail on the Donkey. Six minutes of blindfolded chaos." "Six minutes? Molly, last job I needed six minutes just to tie my shoes." "Which is why you're on distraction, not extraction." "Distraction how?" "You're the clown." "Absolutely not." "Bill." "The last time I wore greasepaint, a toddler bit me." "Then don't get bit this time." "What about the parents?" "Sangria fountain. I spiked it with extra sangria." "That's just more sangria." "Exactly. Nobody suspects more sangria." Bill sighed. "And the dog?" "Pepperoni. Two pounds. Wrapped in a party hat." "You've thought of everything." "I've thought of almost everything. What's the exit?" "Ice cream truck out back. I told the driver we're catering." "Catering what?" "A wedding. For the clown." "Bill, you're the clown." "Which makes it my wedding, which makes it convincing." Molly stared at him. "Fine. Grab the goody bags on the way out." "Obviously. I'm a professional."
created_at
"2026-04-24T19:47:02.455Z"
4/24/2026, 7:47:02 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
866
moderation_latency
(null)
generation_time
6838
tokens_prompt
77
tokens_completion
334
native_tokens_prompt
98
native_tokens_completion
484
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"
usage
0.01259
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"1a6ab866-f637-47ef-b6d6-c92f43fb529b"
is_byok
false
latency
865
model_permaslug
"anthropic/claude-4.7-opus-20260416"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777060022-7kOvHY1zSemStthpLtm4"
session_id
(null)
api_type
"completions"
id
"gen-1777060022-JG8XLF6znUqt413lNzFb"
upstream_id
"1a6ab866-f637-47ef-b6d6-c92f43fb529b"
total_cost
0.01259
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
51.93%
Matches word count
n/a
neededClean
false
words
184
100.00%
Dialogue to Total Word Ratio
Ratio: 90.81%, Deviation: 0.81%
neededClean
false
wordsTotal
185
wordsDialogue
168
75.9606%