NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1GCM9SX5NBG8B0B3WN2C64
Run Details
Model:
Inception Mercury 2
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
12.0s
Cost:
$0.008119
Provider:
Inception
Evaluation summary
Score
Evaluator
Details Link
6.09%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
3.0473%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 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 adjusted her oversized sunglasses, even though the party was in a community center gym lit by fluorescent lights. She glanced at the flyer taped to the bulletin board: 'Kids' Birthday Bash – Free Balloons, Cake, and Gifts!' The words made her grin. 'This is the perfect loot,' she whispered to Bill, who was fiddling with a cheap lock pick set. Bill looked up, his eyebrows raised. 'You think we can get past the clown security?' Molly rolled her eyes. 'The clown is just a guy in a red nose. He can't stop us.' They crouched behind a stack of folding chairs, listening to the squeal of a squeaky toy and the distant hum of a karaoke machine. Room smelled of frosting and cheap perfume. 'We need a distraction,' Bill said, tapping his foot. 'Maybe we can set off the balloon popper.' Molly smirked. 'I already ordered a batch of super‑loud party horns. When they blast, the kids will think it's part of the game.' 'And the parents will be too busy filming on their phones,' Bill added, grinning. 'What about the gift table?' Molly asked, peering over the edge of a table covered in wrapping paper. 'That's the gold mine,' Bill replied. 'We just need a way to slip in without tripping over the cake.' Molly pulled out a small, inflatable unicorn from her bag. 'This will float us over the rug. No footprints.' 'Brilliant,' Bill said, admiring the ridiculousness. 'And I have a portable smoke machine. A puff of harmless fog, and the kids will think it's a magic trick.' 'We should wear matching outfits,' Molly suggested, pulling a pink onesie from a hidden compartment. 'If we look like part of the party, nobody will suspect a thing.' 'You look like a unicorn,' Bill laughed. 'And I’ll be the giant teddy bear.' They laughed, the sound echoing off streamers. 'Timing is everything,' Molly said, checking her watch. 'The cake will be cut at 3:15. That's when lights dim for clown’s balloon finale.' 'Then we move in at 3:14,' Bill replied, tapping his knuckles on the table. 'We’ll grab the presents, slip out with the unicorn float, and vanish before the applause.' 'What about the security camera?' Molly asked, pointing at a lens perched above the doorway. 'We’ll cover it with a reflective foil,' Bill said, pulling a roll from his pocket. 'It will bounce the light back and make footage look like a disco ball.' 'And the kids will think it’s a special effect,' Molly added, giggling. 'All right, let’s rehearse,' Bill said, standing up. 'We’ll practice the unicorn float, the horn blast, and the smoke puff. No mistakes.' Molly nodded, her eyes sparkling. 'If we pull this off, we’ll be the only thieves who ever stole a birthday party and got away with it.' They exchanged a high‑five, the sound of clacking like applause. Later, gym was a sea of balloons and squealing kids. Molly floated on the unicorn, Bill puffed harmless smoke, and clown’s finale distracted everyone. They snatched the gift table, tucked the loot into a sack, and slipped out as last balloon popped, leaving only frosting scent behind.
created_at
"2026-03-06T12:01:37.09Z"
3/6/2026, 12:01:37 PM
model
"inception/mercury-2-20260304"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
11596
moderation_latency
(null)
generation_time
11995
tokens_prompt
77
tokens_completion
6644
native_tokens_prompt
60
native_tokens_completion
10821
native_tokens_completion_images
(null)
native_tokens_reasoning
10127
native_tokens_cached
50
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
0.0081195
router
(null)
provider_responses
0
endpoint_id
"c2a24e34-c306-4b4d-9e2f-b162c2d8bf0e"
id
"chatcmpl-80a2b702-4174-4f15-a3d9-37cab849548c"
is_byok
false
latency
50
model_permaslug
"inception/mercury-2-20260304"
provider_name
"Inception"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1772798497-GuU0dwbEYOu3A6DZu29R"
upstream_id
"chatcmpl-80a2b702-4174-4f15-a3d9-37cab849548c"
total_cost
0.0081195
cache_discount
0.00001125
upstream_inference_cost
0
provider_name
"Inception"
Evaluation details
Result
Evaluator
Details
Meta Data
6.09%
Matches word count
n/a
neededClean
false
words
523
0.00%
Dialogue to Total Word Ratio
Ratio: 64.24%, Deviation: 14.24%
neededClean
false
wordsTotal
523
wordsDialogue
336
3.0473%