NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8WFA00EQV5RPETA1F4XMYJ
Run Details
Model:
Gemma 4 26B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.0s
Cost:
$0.000149
Provider:
Io Net
Evaluation summary
Score
Evaluator
Details Link
2.01%
Matches word count
(details)
99.41%
Dialogue to Total Word Ratio
(details)
50.7090%
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
"Are you serious, Bill? A bounce house? That is our entry point?" Molly whispered, eyeing the inflatable castle. "It’s tactical, Molly. High visibility, low security," Bill insisted, adjusting his oversized clown nose. "You look like a failed circus act, not a professional infiltrator." "It’s a disguise! Who suspects a clown of grand larceny?" "The parents. The children. The laws of physics as we bounce uncontrollably toward the cake table." "Focus! Once we hit the playroom, we hit the pile. All the presents. The LEGO sets, the remote-control cars, the high-end tablets. It’s a goldmine." "And how exactly do we exit with six boxes of oversized stuffed animals without looking suspicious?" "We use the balloon animal technique. We hide the loot inside giant, structural balloon giraffes." "That is the most idiotic plan I have ever heard. It’s structurally unsound and physically impossible." "It’s high-risk, high-reward!" "It’s a sugar-fueled disaster waiting to happen. Why couldn't we rob a bank?" "Banks have lasers, Molly. This place only has juice boxes and chaos. Now, grab the pump. It’s showtime."
created_at
"2026-05-10T12:05:57.896Z"
5/10/2026, 12:05:57 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
430
moderation_latency
(null)
generation_time
8916
tokens_prompt
77
tokens_completion
303
native_tokens_prompt
79
native_tokens_completion
274
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.00014885
router
(null)
provider_responses
0
endpoint_id
"0bc24d30-bd26-4fa8-968b-260c0011a4a5"
id
"chatcmpl-ae03b05d98f76398"
is_byok
false
latency
430
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"Io Net"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778414757-GmQvjODrwW3K7pvVhZ5U"
session_id
(null)
api_type
"completions"
id
"gen-1778414757-BzRrDTCYZCIQPO19mUi0"
upstream_id
"chatcmpl-ae03b05d98f76398"
total_cost
0.00014885
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Io Net"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
2.01%
Matches word count
n/a
neededClean
false
words
175
99.41%
Dialogue to Total Word Ratio
Ratio: 92.78%, Deviation: 2.78%
neededClean
false
wordsTotal
180
wordsDialogue
167
50.7090%