NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCSQ3620ABSX97AKXBF0JEJ
Run Details
Model:
Thinking Machines Inkling (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11m 32s
Cost:
$0.037159
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
6.09%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
53.0446%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 black turtleneck, too tight for felony work, and squinted at a floor plan on a frosting-stained napkin. Bill paced behind her, pants jingling with picks, tape, and a rubber giraffe. They intended to rob a children’s party—professionally beneath them yet irresistible. Bill tapped the blueprint. “Gifts sit near the cake table today.” Molly held up a finger. “Seven words, Bill. That is your entire budget spent.” Outside, streamers fluttered like surrender flags. Molly had stalked the birthday mother online, noting every tagged table and blind spot. Bill stuffed the giraffe in his pack. They wore fleece and ski masks—hers had cat ears—fit for Chadwick’s party. The banner screamed joy. Molly killed the garage sensor with a hairclip. Inside, sugar chaos reigned. Twenty kids shrieked, oblivious that adults were stealing wrapped boxes. She signaled Bill past deflated balloons. He tripped over a favor and apologized silently to a unicorn. Molly grabbed the vibrating drone box. Bill stuffed Lego into a duffel disguised as a present, bow upside down. They had four minutes, but the magician fought a clown over a red nose. They escaped past untouched broccoli. The giraffe bobbed in triumph. Bill started the engine. “Not our worst Tuesday.” Molly counted loot. “Wednesday.” Unnoticed. Robbing a child’s party was either their worst job or best. Probably both.
created_at
"2026-07-25T14:08:56.008Z"
7/25/2026, 2:08:56 PM
model
"thinkingmachines/inkling-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
899
moderation_latency
(null)
generation_time
692199
tokens_prompt
75
tokens_completion
8031
native_tokens_prompt
75
native_tokens_completion
9163
native_tokens_completion_images
(null)
native_tokens_reasoning
7667
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
0.03715859
router
(null)
provider_responses
0
endpoint_id
"d6b9d68e-115a-49d7-81cd-1ad1c6942b0e"
id
"chatcmpl-RJJpiYMkec2VCZzdvvV7EAwb"
is_byok
false
latency
55
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-1784988536-zsqHl5wxsLwYEldV9Yld"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784988536-92MXklueIKbRQruBEhns"
upstream_id
"chatcmpl-RJJpiYMkec2VCZzdvvV7EAwb"
total_cost
0.03715859
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
6.09%
Matches word count
n/a
neededClean
false
words
223
100.00%
Dialogue to Total Word Ratio
Ratio: 9.38%, Deviation: 0.63%
neededClean
false
wordsTotal
224
wordsDialogue
21
53.0446%