NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0529GJYP5THWEX40S8DM5M
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
18.8s
Cost:
$0.002751
Provider:
Groq
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
84.40%
Dialogue to Total Word Ratio
(details)
92.1972%
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 and Bill crouch behind the hedges, listening to muffled giggles from the backyard as the party lights flicker softly. Molly: "Alright, Bill, the party starts at eight, and the parents will be busy with clown, so we in at eight fifteen." Bill: "Eight fifteen gives us a window before the kids start opening gifts; perfect." Molly: "We need to neutralize the security camera by covering it with a balloon; love balloons." Bill: "I'll bring a bag of helium; we can tie it to the lens and it will blur." Molly: "What about the cake? We can't leave a trail." Bill: "We distract them with a fire alarm; they'll evacuate, and we grab the presents." Molly: "Smart. And the gift table is beside piñata; we just scoop everything into the tote." Bill: "The tote should be lined with material; those gadgets could set off the alarm." Molly: "Got it. I'll wear the mascot costume; nobody questions a mascot." Bill: "Brilliant. The costume also gives us pockets for the loot." Bill: "And we leave no fingerprints anywhere." Molly: "After we’re out, we meet at the van, drop the haul, split the cash." Bill: "Deal. This is to be the sweetest heist ever."
created_at
"2026-04-24T16:27:16.915Z"
4/24/2026, 4:27:16 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
214
moderation_latency
(null)
generation_time
17553
tokens_prompt
77
tokens_completion
3857
native_tokens_prompt
131
native_tokens_completion
4552
native_tokens_completion_images
(null)
native_tokens_reasoning
4249
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"
usage
0.00275085
router
(null)
provider_responses
0
endpoint_id
"900c5273-4931-4e9f-bb52-57935dd154b4"
id
"chatcmpl-e120da7b-7b7e-42e1-b29e-118fbbe6193d"
is_byok
false
latency
195
model_permaslug
"openai/gpt-oss-120b"
provider_name
"Groq"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777048036-NP4KtP4NWR12FfH0cQJs"
session_id
(null)
api_type
"completions"
id
"gen-1777048036-fZWdOmNdY6dp0seI2rAM"
upstream_id
"chatcmpl-e120da7b-7b7e-42e1-b29e-118fbbe6193d"
total_cost
0.00275085
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Groq"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
201
84.40%
Dialogue to Total Word Ratio
Ratio: 83.58%, Deviation: 6.42%
neededClean
false
wordsTotal
201
wordsDialogue
168
92.1972%