NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DAMJ7V2Y35NPRKYHCFGE80
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
8.7s
Cost:
$0.000953
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
27.17%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
63.5806%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 crouched behind the hedge, peering at the glowing windows of number twelve. Bill squinted at the blueprints, which were actually a child's coloring book. "Right, the plan," Bill whispered. "We go in through the back, grab every present with a bow on it, and vanish." "And the bouncy castle?" Molly asked. "Leave the bouncy castle. Nobody steals a bouncy castle, Molly. That's just rude." A small face appeared at the kitchen window, pressed against the glass. Molly froze. Bill froze. The face stuck out its tongue and disappeared. "Did that kid just make us?" Bill hissed. "Nobody makes us. We're professionals." She adjusted her ski mask, which had a cartoon unicorn printed on it. "Okay. Phase two. Distraction." "What's the distraction?" She held up a piñata shaped like a dinosaur. "We lure the adults out with this, and then we..." "Wait, is that the piñata with the candy?" "Yes, Bill, and we're taking the candy too." Somewhere inside, a man in a rainbow wig began blowing up balloons with alarming enthusiasm. "Fine. But if the clown starts juggling, I'm running."
created_at
"2026-10-08T08:38:49.859Z"
10/8/2026, 8:38:49 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
7564
moderation_latency
(null)
generation_time
8627
tokens_prompt
75
tokens_completion
280
native_tokens_prompt
95
native_tokens_completion
1886
native_tokens_completion_images
(null)
native_tokens_reasoning
1465
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
0.0009525
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448729-55UoGuyvENEDW1O81vWg"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448729-tTxRNI4dhq0Ydba8vkOC"
upstream_id
"msg_011CfpU7GX1miHi2g9mpUX6R"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpU7GX1miHi2g9mpUX6R"
is_byok
false
latency
706
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0009525
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
27.17%
Matches word count
n/a
neededClean
false
words
181
100.00%
Dialogue to Total Word Ratio
Ratio: 49.17%, Deviation: 0.83%
neededClean
false
wordsTotal
181
wordsDialogue
89
63.5806%