NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR927XN21XMAR1QBBG5R7KFY
Run Details
Model:
Gemma 4 26B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 2s
Cost:
$0.004595
Provider:
NextBit
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
99.79%
Dialogue to Total Word Ratio
(details)
93.0841%
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
"Target is the Henderson residence. High-value loot. LEGOs, drones, maybe a rare holographic Pokémon card," Molly hissed, tapping the crayon-drawn map. "Molly, it’s a toddler’s birthday," Bill groaned, leaning back in the getaway van. "The security is basically a bouncy castle and a very distracted nanny." "Don't underestimate the perimeter! There's a clown, Bill." "Clowns aren't sentries. They're just sad men in face paint." "They're unpredictable! One minute it's balloon animals, the next, it's smoke bombs and glitter. We strike during the cake cutting. When the sugar high hits, the guards, the parents, will be totally distracted." "And the exit strategy?" "We blend in. Party hats, juice boxes. We're Uncle Dave and his weird cousin." "I don't look like a Dave." "Tuck in your shirt and act like you enjoy lukewarm pizza. Grab the loot bags!" "Do we get cake?" "Focus, Bill!" "Can I at least wear the propeller hat?" "Only if it covers your shame." "Fine, but I'm stealing a juice box for the road." "Just get the presents!" "Is there a gift registry?" "Don't be ridiculous!" "What if they have a bouncy castle mission?" "Just jump, Bill!"
created_at
"2026-05-10T13:46:47.338Z"
5/10/2026, 1:46:47 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
791
moderation_latency
(null)
generation_time
61949
tokens_prompt
77
tokens_completion
9551
native_tokens_prompt
82
native_tokens_completion
11458
native_tokens_completion_images
(null)
native_tokens_reasoning
9229
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
0.0045955
router
(null)
provider_responses
0
endpoint_id
"e22ce918-7adb-4e4f-b2e2-c6c5b3066b69"
id
"chatcmpl-85b3a437f868a53c"
is_byok
false
latency
754
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"NextBit"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778420807-tIt7isPK9QjSzSbhGP3g"
session_id
(null)
api_type
"completions"
id
"gen-1778420807-Oj3l2JEP6MrJTUli2V20"
upstream_id
"chatcmpl-85b3a437f868a53c"
total_cost
0.0045955
cache_discount
(null)
upstream_inference_cost
0
provider_name
"NextBit"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
189
99.79%
Dialogue to Total Word Ratio
Ratio: 92.15%, Deviation: 2.15%
neededClean
false
wordsTotal
191
wordsDialogue
176
93.0841%