NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR91A5JAJM4VCBZW5VTM790V
Run Details
Model:
Gemma 4 31B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
58.6s
Cost:
$0.001142
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
2.01%
Matches word count
(details)
53.75%
Dialogue to Total Word Ratio
(details)
27.8816%
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
"Right, the target is the living room. High density of Lego sets," Molly said. "What about the cake?" "We aren't here for cake, Bill. We're here for the high-value electronics. The iPads, the remote-control drones, the fancy building kits." "I'm just saying, it's a chocolate gateau with fresh raspberries." "Focus! We enter through the dog door at fourteen-hundred. I'll create a strategic diversion with the industrial bubble machine." "Bubbles? That's not a diversion, that's an invitation." "Exactly. The children will swarm the machine, creating a chaotic perimeter. You swoop in, grab the pile of wrapped boxes, and exit via the patio." "Do I wear a disguise?" "You're wearing a giant panda suit, Bill. You're the hired entertainment." "The head is incredibly itchy." "Itch through the pain for the Nintendo Switch, Bill!" "Fine. But if there's a piƱata, I'm hitting it. I'm hitting it hard." "Deal. Now, check your stopwatch." "I forgot it." "I genuinely hate you." "Does the panda suit have pockets?" "No." "Then how do I carry the Lego?" "In your arms, you idiot!"
created_at
"2026-05-10T13:30:32.401Z"
5/10/2026, 1:30:32 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
227
moderation_latency
(null)
generation_time
58117
tokens_prompt
77
tokens_completion
2062
native_tokens_prompt
81
native_tokens_completion
2251
native_tokens_completion_images
(null)
native_tokens_reasoning
1779
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
0.0011417
router
(null)
provider_responses
0
endpoint_id
"576fca5b-f09c-4bda-b560-9989c39ac3ab"
id
"oiXsVzM-4nba6j-9f994c90972214a7"
is_byok
false
latency
197
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"Together"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778419832-fgtYC2Q92OxuhzZ28HVd"
session_id
(null)
api_type
"completions"
id
"gen-1778419832-ZFBLLHGJQmDkr6K3gmlg"
upstream_id
"oiXsVzM-4nba6j-9f994c90972214a7"
total_cost
0.0011417
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
2.01%
Matches word count
n/a
neededClean
false
words
175
53.75%
Dialogue to Total Word Ratio
Ratio: 98.88%, Deviation: 8.88%
neededClean
false
wordsTotal
178
wordsDialogue
176
27.8816%