NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-09-01M4FYA5XA9P5M8F4RKXY6VTBZ
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.4s
Cost:
$0.000915
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
99.82%
Dialogue to Total Word Ratio
(details)
49.9122%
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
The van idled behind a bouncy castle warehouse on Maple Street, headlights off for dramatic effect. Molly spread the blueprints across the dashboard while Bill chewed a granola bar with suspicious enthusiasm. Somewhere inside the house, a bouncy castle squeaked and a child screamed happily about cake. "Presents are in the living room," Molly whispered. "Behind the piƱata." Bill squinted at the sketch, which had a doodle of a unicorn in one corner. He pulled on a ski mask decorated with cartoon ducks. Molly pointed through the windshield at a clown wrestling a fog machine near the gate. Gerald was supposed to keep the parents distracted, though he had already been sprayed with glitter twice and seemed to be enjoying it far too much. Bill sighed and adjusted his fake mustache. Molly lifted a cage containing a sleepy hamster wearing a tiny top hat, their cover prop for the magic act. "Ready?" Bill asked. Molly grinned. "Two o'clock. We slip in, grab everything glittery, and vanish."
created_at
"2026-10-09T09:01:09.936Z"
10/9/2026, 9:01:09 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2415
moderation_latency
(null)
generation_time
10427
tokens_prompt
75
tokens_completion
485
native_tokens_prompt
95
native_tokens_completion
1812
native_tokens_completion_images
(null)
native_tokens_reasoning
1443
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
0.0009155
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791536469-cPJqbuxpqKmEFdxSjYje"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791536469-Brg4F5nE356p0IR9Nizk"
upstream_id
"msg_011CfrPcy43R7E2M4upWb82E"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfrPcy43R7E2M4upWb82E"
is_byok
false
latency
689
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0009155
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
0.00%
Matches word count
n/a
neededClean
false
words
166
99.82%
Dialogue to Total Word Ratio
Ratio: 12.05%, Deviation: 2.05%
neededClean
false
wordsTotal
166
wordsDialogue
20
49.9122%