NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4D9WRNX5MXB7HT6W229GFR3
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.8s
Cost:
$0.000156
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
18.3940%
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 go in through the back window while the clown is doing balloon animals." "What if the clown spots us?" "Clowns don't spot anything, Bill. They're too busy honking that horn. Now, the presents are stacked by the piano. Mostly tricycles and a suspicious amount of socks." "Socks? Who gives socks to a six-year-old?" "Grandmas, Bill. Grandmas. Focus. Once we've got the loot, we slip out during the cake fight." "Cake fight? Is that a real thing?" "Every birthday party is a real thing. Trust me, I've been to forty of them." "Forty? Why?" "Undercover work. Don't ask. Now, grab that sack and stop eating the frosting." "It's for morale." "Your morale can wait until we're in the getaway van, Bill."
created_at
"2026-10-08T08:25:50.023Z"
10/8/2026, 8:25:50 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
732
moderation_latency
(null)
generation_time
2796
tokens_prompt
75
tokens_completion
190
native_tokens_prompt
95
native_tokens_completion
292
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
0.0001555
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791447950-iK4M56s6CDzRBavWHNFX"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791447950-3TjrP02e2RfT6nBkUQYk"
upstream_id
"msg_011CfpT7nc91RFUhn8e5jeQD"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpT7nc91RFUhn8e5jeQD"
is_byok
false
latency
732
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0001555
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
126
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
128
wordsDialogue
128
18.3940%