NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8ZWZ4JJ8K2SR0V3MBQETJ4
Run Details
Model:
Gemma 4 26B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 21s
Cost:
$0.003696
Provider:
Cloudflare
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
97.9912%
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
"Listen, Bill," Molly whispered, spreading a crayon-drawn map across the table. "Is that a drawing of a bouncy castle?" Bill asked. "It's the tactical layout, Bill! Focus." "But Molly, it's a six-year-old's birthday. There's no jewelry. Just LEGO and maybe some scented markers." "That's where you're wrong. The high-end stuff is in the big red box near the clown." "The clown? You want me to pickpocket a clown?" "No, you grab the loot while I distract the magician with a fake existential crisis." "A crisis? Is that a standard diversion?" "It works every time. People get uncomfortable and look away." "And the cake?" Bill asked. "Is the cake part of the haul?" "Professionalism, Bill! We aren't here for frosting." Molly glared at him. "Stay focused. We go in during the piƱata smash. It's the perfect sonic cover." "Right. Smash the candy, grab the toys, avoid the juice boxes. Got it." "And for heaven's sake, don't get distracted by the face painting." "No promises. Glitter is hard to resist." "If you end up with a butterfly nose, you're fired." "Fine, fine. But I am not promising anything about the cupcakes." "Bill!" "Fair enough."
created_at
"2026-05-10T13:05:51.257Z"
5/10/2026, 1:05:51 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
357
moderation_latency
(null)
generation_time
141011
tokens_prompt
77
tokens_completion
10546
native_tokens_prompt
81
native_tokens_completion
12292
native_tokens_completion_images
(null)
native_tokens_reasoning
10246
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
0.0036957
router
(null)
provider_responses
0
endpoint_id
"e2a16fa6-1f65-413e-9ecb-93901089ddb1"
id
"id-1778418351520"
is_byok
false
latency
255
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"Cloudflare"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778418351-Oofebs9JUuaNWcymwgqz"
session_id
(null)
api_type
"completions"
id
"gen-1778418351-xsZlc8lVvIeN8dDF52bs"
upstream_id
"id-1778418351520"
total_cost
0.0036957
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Cloudflare"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
192
100.00%
Dialogue to Total Word Ratio
Ratio: 90.82%, Deviation: 0.82%
neededClean
false
wordsTotal
196
wordsDialogue
178
97.9912%