NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR90H5BH78Y4B143JK0J7PYK
Run Details
Model:
Gemma 4 31B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 33s
Cost:
$0.000949
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.21%
Matches word count
(details)
88.02%
Dialogue to Total Word Ratio
(details)
44.1162%
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
Molly pointed at the map. "The perimeter is secure, Bill." "It's a bouncy castle, Molly. Not a fortress." "Exactly. The tactical advantage is immense." "We're stealing from seven-year-olds. This is a new low for us." "We're liberating overpriced plastic blocks and LEGO sets. Now, the distraction." "A fake fire alarm?" "Too cliché. We release the balloons." "The balloons?" "One hundred helium balloons. In the ensuing chaos, we swoop the gift table." "What about the clown? He looks shifty." "The clown is a variable. If he resists, you hit him with the oversized mallet." Bill frowned. "Where did we even get an oversized mallet?" "I stole it from the party supply store yesterday. Now, put on the tutu." "I am absolutely not wearing a tutu." "Blending in is key, Bill. You're an enthusiastic aunt from out of town." "I have a full beard, Molly. A very prominent, scratchy beard." "A bearded aunt. It's a trend in the city. Now move!" "I can't believe I'm doing this." "Stop complaining and start dancing, Aunt Bill."
created_at
"2026-05-10T13:16:52.988Z"
5/10/2026, 1:16:52 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
782
moderation_latency
(null)
generation_time
82299
tokens_prompt
77
tokens_completion
2335
native_tokens_prompt
82
native_tokens_completion
2470
native_tokens_completion_images
(null)
native_tokens_reasoning
2065
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
0.00094926
router
(null)
provider_responses
0
endpoint_id
"29b94af5-d8f8-419a-9cf1-ae1f2831142b"
is_byok
false
latency
108
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"Venice"
status
429
1
endpoint_id
"9d4644e9-a5e5-41f4-b810-d75f484d2c24"
is_byok
false
latency
25
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"Parasail"
status
429
2
endpoint_id
"69279254-6a96-4e9d-abc6-ea76e6bf8e97"
is_byok
false
latency
10077
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"Novita"
status
504
3
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RL9PeqJP8oVJrfoI7tgKHCwu"
is_byok
false
latency
61
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778419012-LXzOQ84vyyIpupKYQcSf"
session_id
(null)
api_type
"completions"
id
"gen-1778419012-JQfNUA83QLBS7MPsO5Bk"
upstream_id
"chatcmpl-RL9PeqJP8oVJrfoI7tgKHCwu"
total_cost
0.00094926
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.21%
Matches word count
n/a
neededClean
false
words
172
88.02%
Dialogue to Total Word Ratio
Ratio: 95.98%, Deviation: 5.98%
neededClean
false
wordsTotal
174
wordsDialogue
167
44.1162%