NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR91P84RRSW6D3K4356J9WY6
Run Details
Model:
Gemma 4 26B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
6m 32s
Cost:
$0.005422
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.75%
Dialogue to Total Word Ratio
(details)
99.8753%
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 tapped the map. "Listen, Bill. The target is the Miller residence. Saturday, two PM. The theme is 'Intergalactic Space Explorers.'" "A space party?" Bill asked. "Are we stealing rocket ships?" "No, you idiot," Molly snapped. "We're stealing the loot. The pile of wrapped boxes under the tree. It's a goldmine of Lego sets, high-end drones, and tablets." "What about the defense system? I heard there's a laser grid or a high-tech security dog." "It's a seven-year-old in a dinosaur suit, Bill," she said. "That's the only defense you'll face." "That sounds terrifying. What if there's bouncy castle interference affecting our sonar?" "We use the bouncy castle for extraction," Molly replied. "We jump in, grab the goods, and bounce out the side window." "And the juice boxes? Are they part of the haul?" Bill asked. "Forget the juice boxes. Focus on the Nintendo Switches." "Can I at least wear a tactical mask?" "No, you'll wear a red clown nose. It's the perfect camouflage in a room full of birthday chaos." "A clown nose? This is the lowest I've ever sunk!" Bill cried. "Quiet! It's for the craft, Bill. Now, pack the bags and grab the glitter-free gloves. We move at dawn."
created_at
"2026-05-10T13:37:08.255Z"
5/10/2026, 1:37:08 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
321
moderation_latency
(null)
generation_time
392170
tokens_prompt
77
tokens_completion
10344
native_tokens_prompt
82
native_tokens_completion
15930
native_tokens_completion_images
(null)
native_tokens_reasoning
10039
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
0.00542194
router
(null)
provider_responses
0
endpoint_id
"d71c6981-347d-4622-a86b-2c9e5d0f2c6c"
id
"chatcmpl-R3d67X4C2Wf9yFCFgNd18hdO"
is_byok
false
latency
197
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778420228-IeASXOXB4Jxpr64nVdGl"
session_id
(null)
api_type
"completions"
id
"gen-1778420228-u6D4irbOFHLIrQVzh50a"
upstream_id
"chatcmpl-R3d67X4C2Wf9yFCFgNd18hdO"
total_cost
0.00542194
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
201
99.75%
Dialogue to Total Word Ratio
Ratio: 92.23%, Deviation: 2.23%
neededClean
false
wordsTotal
206
wordsDialogue
190
99.8753%