NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DA1VPEWC3Y038TE6FR0TBY
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.1s
Cost:
$0.000166
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
49.9997%
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
"Okay, Bill, the plan is simple," Molly whispered, crouching behind the bounce castle. "We slip through the back gate, grab every present with a bow on it, and vanish before the clown finishes his balloon animals." "Simple? Molly, there's a seven-year-old in a cape guarding the gift table." "He's a distraction. Nobody suspects a kid in a cape." "I suspect him. He's looking right at us." "Then we wave. Friendly. Like we're the uncle who forgot the sprinkles for the cupcakes." "I don't have an uncle." "Neither do I, Bill, that's why we're such good liars." She peeked over the castle wall. "Okay, three pink boxes, two giant ones shaped like unicorns. Those are mine." "What about the one that's ticking?" "That's the piñata. Leave it." "Molly, the piñata is ticking." "Then we run faster."
created_at
"2026-10-08T08:28:36.951Z"
10/8/2026, 8:28:36 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
735
moderation_latency
(null)
generation_time
3016
tokens_prompt
75
tokens_completion
207
native_tokens_prompt
95
native_tokens_completion
313
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"
service_tier
"default"
usage
0.000166
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448116-eq8g74rbJGfRcdhhQASZ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448116-0FXSAN01cXj7Ur8o7oJL"
upstream_id
"msg_011CfpTL6HMepz6XBogMdF1K"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTL6HMepz6XBogMdF1K"
is_byok
false
latency
735
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.000166
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
135
100.00%
Dialogue to Total Word Ratio
Ratio: 90.51%, Deviation: 0.51%
neededClean
false
wordsTotal
137
wordsDialogue
124
49.9997%