NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCXQFHJW5BSP6EGFT0MT5MY
Run Details
Model:
Thinking Machines Inkling (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
2m 24s
Cost:
$0.006574
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Count dialogue tags
(details)
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
The bell above the door chimed, bringing in a gust of cinnamon-scented air. "You're early. The sourdough isn't out for another ten minutes." "I didn't come for bread." "Then you came for gossip. Everyone else does." "There's talk about the missing ledger from the library auction." "And you're asking me? I knead dough, not detective novels." "Mrs. Peabody said she saw someone in a flour-dusted coat leaving through the back alley last Tuesday." "That could be half the town. We all wear white." "This wasn't a baker's coat. It was wool. Dark gray." "Dark gray wool in July? That'd be suspicious, all right." "Exactly. And she mentioned a sweet smell, not lavender—almond extract." The mixer hummed in the background. A tray of croissants slid onto the cooling rack. "Almond extract. That's my grandmother's glaze recipe. Only three people have it." "Name them." "Not until you buy a danish. I'm not running a charity interrogation." "Fine. One raspberry. Now—who are the three?" "Me, my sister in Vermont, and old Mr. Holloway before he... well. Before." "Before he died?" "Before he stopped returning my calls. There's a difference." "Not in a court of law there isn't." "Are you accusing me?" "I'm accusing the croissant of being too flaky. That's all."
created_at
"2026-07-25T15:19:02.973Z"
7/25/2026, 3:19:02 PM
model
"thinkingmachines/inkling-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
823
moderation_latency
(null)
generation_time
143792
tokens_prompt
78
tokens_completion
1778
native_tokens_prompt
76
native_tokens_completion
1611
native_tokens_completion_images
(null)
native_tokens_reasoning
1446
native_tokens_cached
32
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
"stop"
service_tier
(null)
usage
0.00657399
router
(null)
provider_responses
0
endpoint_id
"d6b9d68e-115a-49d7-81cd-1ad1c6942b0e"
id
"chatcmpl-RqIZlR7S4uUnFyHbyJKcsj9H"
is_byok
false
latency
74
model_permaslug
"thinkingmachines/inkling-20260715"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784992743-iQ9mQOdFcOhDWeQjo194"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784992743-oUOJsFKQGlm1gy22G5Zx"
upstream_id
"chatcmpl-RqIZlR7S4uUnFyHbyJKcsj9H"
total_cost
0.00657399
cache_discount
0.00002656
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)