NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DYWV39JF168X5A31BX0N06
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 58s
Cost:
$0.021593
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.98%
Dialogue to Total Word Ratio
(details)
99.9889%
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 tapped the blueprints. "Right, Bill, the score's in the conservatory. Twenty-three presents, and we're taking every last one." "Twenty-three? For one six-year-old?" "Which is why she's spoiled rotten. Our inside woman is Grandma Doris. She's left the back door open." "Doris is a grandma. Grandmas don't do crime." "Doris cheats at bingo, Bill. She's a natural." "So we're breaking in?" "Breaking in is messy. We're strolling in." "And the magician? He's booked for two o'clock." "Cancelled this morning. Which means we're the magicians now." "We don't know any magic, Molly." "We know how to make things vanish. That's basically magic." "Why are we in an ice cream van?" "Nobody suspects an ice cream van." "Everybody suspects an ice cream van. You can hear it from three streets away." "Nobody can say we're sneaking about." "What about the birthday girl? The one who bit the postman?" "Poppy? She's six. Keep your distance, and she'll never notice." A small face appeared at the window, nose pressed to the glass. "Molly, she's here." "Smile, Bill. Be a magician." "She's holding a clipboard and a whistle." "Good afternoon," said Poppy. "Are you the magicians?" "Absolutely, sweetheart." "Then make the presents disappear." "Abracadabra!" "Abra-RUN!"
created_at
"2026-10-08T14:32:52.595Z"
10/8/2026, 2:32:52 PM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2511
moderation_latency
(null)
generation_time
177803
tokens_prompt
75
tokens_completion
6107
native_tokens_prompt
95
native_tokens_completion
43166
native_tokens_completion_images
(null)
native_tokens_reasoning
42654
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
0.0215925
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791469972-h4cm88Yxe75ggPjHDEHf"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791469972-QFaQiLbAyqQzRYYpULQ8"
upstream_id
"msg_011Cfpw7AsaMEz9xGuYgvmBj"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011Cfpw7AsaMEz9xGuYgvmBj"
is_byok
false
latency
809
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0215925
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Claude Platform on AWS"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
99.98%
Dialogue to Total Word Ratio
Ratio: 91.22%, Deviation: 1.22%
neededClean
false
wordsTotal
205
wordsDialogue
187
99.9889%