NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFJ95T4A6NC4AMSKD97YQ53
Run Details
Model:
Stealth: Hunter Alpha
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
15.0s
Cost:
$0.000000
Provider:
Stealth
Evaluation summary
Score
Evaluator
Details Link
0.01%
Matches word count
(details)
14.72%
Dialogue to Total Word Ratio
(details)
7.3669%
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
The air smelled of rain and cheap coffee in the cramped garage. Molly peered through a spyglass at the blueprint tacked to the wall. Molly: “Security’s light. One clown named Boffo, half-asleep at the gate.” Bill: “Boffo? He owes me twenty bucks. This is perfect.” Molly: “Your entire plan relies on a clown’s debt?” Bill: “No! It relies on distraction. We trigger the piñata.” Molly: “The… piñata?” Bill: “It’s a Trojan horse, Moll. We pack it with smoke pellets. When it breaks, chaos.” Molly: “And in the chaos, we grab the loot.” Bill: “The mountain of presents. Think of the teddy bears. The video games.” Molly: “You’ve gone soft. We’re after the deluxe train set. It’s got real brass fittings.” Bill: “I’m not soft! I’m… diversifying the payload. Teddy bears fence easily.” Molly: “Fine. But if Boffo recognizes you, we’re stuck doing the ‘Chicken Dance’ as cover.” Bill: “A worthy sacrifice for the train. Now, about your clown nose… it’s slightly askew.” Molly: “It’s supposed to be. It’s ‘ironic.’”
created_at
"2026-03-11T23:04:03.152Z"
3/11/2026, 11:04:03 PM
model
"openrouter/hunter-alpha"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3897
moderation_latency
(null)
generation_time
14965
tokens_prompt
77
tokens_completion
689
native_tokens_prompt
2111
native_tokens_completion
602
native_tokens_completion_images
(null)
native_tokens_reasoning
379
native_tokens_cached
1984
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0
router
(null)
provider_responses
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773270243-YLd2yCEZIX6GvLje6yby"
upstream_id
"gen-1773270243-YLd2yCEZIX6GvLje6yby"
total_cost
0
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Stealth"
Evaluation details
Result
Evaluator
Details
Meta Data
0.01%
Matches word count
n/a
neededClean
false
words
169
14.72%
Dialogue to Total Word Ratio
Ratio: 78.24%, Deviation: 11.76%
neededClean
false
wordsTotal
170
wordsDialogue
133
7.3669%