NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCQSX1Z54VAQ21HSFN51AG5
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
14.4s
Cost:
$0.021415
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
89.89%
Dialogue to Total Word Ratio
(details)
92.9366%
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 hood of the van, smoothing them with the reverence of a surgeon, though the blueprints were technically a placemat from Pizza Chalet and the bouncy castle had been drawn in orange crayon. She had labeled the gift table LOOT MOUNTAIN and underlined it three times, which felt professional. Bill had come dressed as a clown. Not a subtle clown, either. He had committed to the bit before anyone approved the bit, and his wig smelled faintly of gasoline, which he refused to explain. "Nobody ever suspects a clown," he said, honking his nose with great solemnity. Molly looked at him for a long moment. She had once robbed a jewelry exchange in Antwerp with a partner who could crack a vault by listening to it breathe. Now she had a man in size nineteen shoes eating a cold slice over her floor plan. The plan was straightforward. Bill would enter at two, arranged as entertainment, and perform balloon animals for eleven seven-year-olds until their parents wept with gratitude. Molly would arrive as an aunt, vague and unquestioned, carrying an enormous empty gift bag. During the piñata frenzy—chaos, blindfolds, sanctioned violence—the presents would simply relocate. "Balloons in," she said. "Presents out."
created_at
"2026-07-25T13:35:30.888Z"
7/25/2026, 1:35:30 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3928
moderation_latency
(null)
generation_time
14254
tokens_prompt
75
tokens_completion
515
native_tokens_prompt
93
native_tokens_completion
838
native_tokens_completion_images
(null)
native_tokens_reasoning
197
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
0.021415
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNs4nf3KKZbHTcdUPBvH"
is_byok
false
latency
1286
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-1784986530-aYG2kcS0ctEcO8QFj0Yi"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986530-d85574HT6ZzFZSDSwdl8"
upstream_id
"msg_011CdNs4nf3KKZbHTcdUPBvH"
total_cost
0.021415
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
95.99%
Matches word count
n/a
neededClean
false
words
208
89.89%
Dialogue to Total Word Ratio
Ratio: 4.29%, Deviation: 5.71%
neededClean
false
wordsTotal
210
wordsDialogue
9
92.9366%