NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCVJC24KHF2ST5GKPQ6VWST
Run Details
Model:
Thinking Machines Inkling (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
45.8s
Cost:
$0.015486
Provider:
Together
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
Flour dusted the counter like snow that refused to melt. The older woman slid a plate of lemon bars across the worn pine. "You heard about the missing cookbook?" The younger one stopped wiping the display case. "The one from Mrs. Peabody's estate?" "Found open in the garden shed this morning. Pages torn out." The older woman didn't touch her coffee. "Which pages?" "The ones with the almond torte. The same recipe she served the night before she died." "You're saying someone stole it to hide the ingredients?" "I'm saying the police aren't asking about the bakery deliveries." The oven timer chimed, but neither moved. The younger woman glanced toward the back room. "So who brought her the marzipan?" "That's just it. No one ordered any. Yet there it was, wrapped in wax paper, on her doorstep." She tapped the counter. "Maybe she made it herself." "With arthritic hands? Besides, the wrapper had the old train station stamp. Nobody's used that ink since the depot closed." The younger woman passed a fresh cup across the counter. "Then we need to check the delivery logs." "Burned them all. Every record from Tuesday to Thursday." "Convenient." "Exactly. Now, about these lemon bars—do they taste like regret, or am I just paranoid?" "Paranoid. But have another. We'll need the sugar."
created_at
"2026-07-25T14:41:18.416Z"
7/25/2026, 2:41:18 PM
model
"thinkingmachines/inkling-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
447
moderation_latency
(null)
generation_time
45500
tokens_prompt
78
tokens_completion
3961
native_tokens_prompt
76
native_tokens_completion
3805
native_tokens_completion_images
(null)
native_tokens_reasoning
3511
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
"stop"
service_tier
(null)
usage
0.01548625
router
(null)
provider_responses
0
endpoint_id
"9911deb9-f44e-4e18-87fe-9d7b60acee72"
id
"otYVn9B-6z2FuN-a20becba8d93179d"
is_byok
false
latency
442
model_permaslug
"thinkingmachines/inkling-20260715"
provider_name
"Together"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784990478-kVIviAjHLZkzGx4rBaBx"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784990478-HbHd7hcFbzLeZ9PvNe5l"
upstream_id
"otYVn9B-6z2FuN-a20becba8d93179d"
total_cost
0.01548625
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
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)