NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZV6D77DBXRXB4BNJ2XP1PY
Run Details
Model:
Claude Opus 4.7
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.5s
Cost:
$0.011265
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
73.03%
Dialogue to Total Word Ratio
(details)
86.2038%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 blueprints across the folding card table, pinning the corners down with half-empty juice boxes she'd stolen for reconnaissance purposes. The layout of the Peterson residence glowed under her desk lamp like a treasure map drawn by a kindergartner, which, technically, it had been. Bill hunched beside her, chewing the end of a bendy straw with the intensity of a man defusing a bomb. The party was scheduled for Saturday at two o'clock, which gave them exactly seventy-two hours to perfect what Molly had dubbed Operation Cake Walk. Ten children. Approximately forty-seven gift bags. One bouncy castle that would serve as both distraction and, potentially, getaway vehicle if things went sideways. Bill tapped the backyard perimeter, where a clown named Mister Giggles was contracted to perform magic tricks between two and three. "Clown's ours by two-fifteen," Bill muttered. Molly nodded, circling the piñata location in red marker. The piñata itself was irrelevant, but the swinging stick posed a genuine threat to their escape route along the hedgerow. She sketched in little stick figures representing parents, assigning each one a threat level based on caffeine intake and apparent fitness, and underlined the grandmother twice.
created_at
"2026-04-24T13:34:46.004Z"
4/24/2026, 1:34:46 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
656
moderation_latency
218
generation_time
7239
tokens_prompt
77
tokens_completion
318
native_tokens_prompt
98
native_tokens_completion
431
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
0.011265
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"21f389ee-d06e-42bb-b65c-36b85cad8cae"
is_byok
false
latency
656
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-1777037686-kBDhwlbW20s5ImdaZjIX"
session_id
(null)
api_type
"completions"
id
"gen-1777037686-nQvQCnv4bYdie206SeDi"
upstream_id
"21f389ee-d06e-42bb-b65c-36b85cad8cae"
total_cost
0.011265
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
195
73.03%
Dialogue to Total Word Ratio
Ratio: 2.51%, Deviation: 7.49%
neededClean
false
wordsTotal
199
wordsDialogue
5
86.2038%