NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ067EE78G004K9XYK193ZF5
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.9s
Cost:
$0.002261
Provider:
Groq
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 slinked behind the balloon arch, her eyes scanning the chaos of the backyard. The clink of plastic cups and squeals of toddlers formed a bizarre symphony that made Bill grin like a cat with a stolen fish. She nudged the oversized dinosaur piñata, testing its wobble, then slipped a lock‑pick into the pocket of her jacket. Bill crouched by the candy table, his fingers itching for the glittering wrappers. "First the gift table," Molly hissed, tapping a finger against the stacked presents. "Then the cake," Bill replied, eyes flicking to the towering frosting mountain. "Speed up, the kids will notice soon," Bill whispered. They moved like ninjas in oversized party shoes, ducking under a stream of confetti that fell like rain. The host chased a runaway clown balloon, giving them a perfect window. Molly lifted the tarp covering the gifts, exposing a mountain of wrapped boxes. "Watch the cat," she muttered. "Ready?" she whispered, a grin spreading across her face. "Now!" "Quick!" Bill nodded, his breath puffing in the cool night air. Together they hoisted the loot, their laughter muffled by the distant giggles of children, and vanished into the night, leaving only empty ribbons and a party planner.
created_at
"2026-04-24T16:47:34.357Z"
4/24/2026, 4:47:34 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
153
moderation_latency
(null)
generation_time
5383
tokens_prompt
77
tokens_completion
3811
native_tokens_prompt
131
native_tokens_completion
3735
native_tokens_completion_images
(null)
native_tokens_reasoning
3459
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
0.00226065
router
(null)
provider_responses
0
endpoint_id
"900c5273-4931-4e9f-bb52-57935dd154b4"
id
"chatcmpl-9238e5b5-4129-47d5-a3eb-b9545a893ead"
is_byok
false
latency
148
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-1777049254-2swhOj2UjAoOaPQ1UJ2S"
session_id
(null)
api_type
"completions"
id
"gen-1777049254-OYMxk2831spkUqQESnZv"
upstream_id
"chatcmpl-9238e5b5-4129-47d5-a3eb-b9545a893ead"
total_cost
0.00226065
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
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%