NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DA57SWQ1D081FEYJNYQNRE
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.5s
Cost:
$0.000214
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
6.09%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
21.4393%
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
"Right, Bill, here's the plan. We slip in through the bouncy castle vent, grab every present with a bow on it, and be out before the clown finishes his balloon animals." "Hang on, Molly. Why do we need the vent? The front door's wide open. Mrs. Pickering's been yelling about the ice cream for an hour." "Because the front door has a seven-year-old guarding it, Bill. Tiny lad, pirate hat, carries a plastic sword." "Pirate hat? That's a serious threat." "Deadly. Now, the tricky bit is the piñata. Nobody touches the piñata." "Why not?" "Because I'm not explaining to a crowd of toddlers why a sack of sweets fell out of the sky onto a grandad." "Fair point. What about the cake?" "Cake is off limits. Sticky fingers leave evidence." "And if the clown spots us?" "We wave, we smile, and we hand him a balloon. Nobody suspects a clown." "Molly, I'm starting to think this is the worst heist ever." "Relax. Tell me again how many presents we're taking?" "Forty-two." "Perfect. Let's go steal some birthdays."
created_at
"2026-10-08T08:30:27.653Z"
10/8/2026, 8:30:27 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
741
moderation_latency
(null)
generation_time
3445
tokens_prompt
75
tokens_completion
263
native_tokens_prompt
95
native_tokens_completion
409
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
0.000214
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448227-iRpRKFxmMZwnv1ZW8kJl"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448227-1qyrwdctRTEtT806QS8k"
upstream_id
"msg_011CfpTUGCPDosHUyyaXzn9Q"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTUGCPDosHUyyaXzn9Q"
is_byok
false
latency
741
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.000214
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
6.09%
Matches word count
n/a
neededClean
false
words
177
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
180
wordsDialogue
180
21.4393%