NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0G1T63KF4B6DAYC62KQYKX
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
6.7s
Cost:
$0.010740
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
59.33%
Dialogue to Total Word Ratio
(details)
79.5386%
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 unrolled the blueprint across the sticky diner table, flattening it with a ketchup bottle and two half-eaten pancakes. The floor plan of the Fun Barn glowed under the neon light, every ball pit and piƱata circled in red marker. She tapped the emergency exit with a chewed fingernail, then circled the present table three times for emphasis. Bill squinted at the diagram, nursing coffee that had gone cold somewhere around his third existential crisis of the morning. He had never robbed a seven-year-old before, and his conscience, which usually slept through these conversations, was now wide awake and demanding a lawyer. "Clowns scare me," Bill muttered. Molly didn't look up. She was calculating wrapping paper square footage, estimating getaway weight, factoring in the structural integrity of the average gift bag. Outside, rain smeared against the window like a bad alibi. Bill pictured tiny cone hats, tiny accusing faces, tiny lawyers. Molly slid him a clown mask across the table with the solemnity of a priest passing communion. He accepted it. Somewhere, a child was currently writing a thank-you note for gifts they would never receive, and Bill tried very hard not to think about that.
created_at
"2026-04-24T19:39:15.527Z"
4/24/2026, 7:39:15 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
910
moderation_latency
(null)
generation_time
6650
tokens_prompt
77
tokens_completion
306
native_tokens_prompt
98
native_tokens_completion
410
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
0.01074
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"ca139e0e-0276-4d6d-b602-5489294503cf"
is_byok
false
latency
907
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-1777059555-n1SCbSiMsZxlSqzqS8KA"
session_id
(null)
api_type
"completions"
id
"gen-1777059555-XDgg7qTyYfFxOq5758qz"
upstream_id
"ca139e0e-0276-4d6d-b602-5489294503cf"
total_cost
0.01074
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
196
59.33%
Dialogue to Total Word Ratio
Ratio: 1.50%, Deviation: 8.50%
neededClean
false
wordsTotal
200
wordsDialogue
3
79.5386%