NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ08YS37CD59PTD0K0ADS9QV
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
16.0s
Cost:
$0.001659
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.95%
Dialogue to Total Word Ratio
(details)
99.9747%
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 perched on the dented folding chair that had once served as a makeshift throne at the preschool bake‑sale, scanning the rainbow‑striped balloons bobbing lazily above the kiddie table. Bill crouched behind a towering stack of inflatable dinosaurs, his fingers twitching as if ready to pull a lever on a cartoon heist. The air smelled of sawdust and melted chocolate, a scent that reminded them both of their first botched caper involving a piñata and a malfunctioning firecracker. They whispered plans in hushed tones, careful not to attract the watchful eye of Mrs. Pettigrew, the party’s overly enthusiastic coordinator who wore a glittery badge reading “Chief Fun Officer.” Molly whispered, "We skip the cake." Bill replied, "Grab the gift table." Molly added, "Don't touch the balloons." Bill muttered, "Silent as sneaky ninjas." Molly grinned, "All loot, no tears." Their scheme hinged on a precise timing: first disable the clown’s squeaky horn with a well‑placed sock, then sprint to the pile of wrapped wonders while the children were distracted by a surprise bubble‑machine demonstration. With a wink, Molly slipped a black mask over her eyes, and Bill tightened his grip on the stolen tote bag, rehearsing triumphant exit through backyard gate.
created_at
"2026-04-24T17:35:16.085Z"
4/24/2026, 5:35:16 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
187
moderation_latency
(null)
generation_time
15076
tokens_prompt
77
tokens_completion
2816
native_tokens_prompt
114
native_tokens_completion
2737
native_tokens_completion_images
(null)
native_tokens_reasoning
2494
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
0.0016593
router
(null)
provider_responses
0
endpoint_id
"38ee5d29-5f91-486e-8485-eaf2408ee328"
id
"chatcmpl-RDvQCvSyljPj7v8jopp5oQgr"
is_byok
false
latency
87
model_permaslug
"openai/gpt-oss-120b"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777052116-Bhfwr7HU87bgzFTBPjHF"
session_id
(null)
api_type
"completions"
id
"gen-1777052116-cmjqhDq6nAQ1tNSbuDnp"
upstream_id
"chatcmpl-RDvQCvSyljPj7v8jopp5oQgr"
total_cost
0.0016593
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
200
99.95%
Dialogue to Total Word Ratio
Ratio: 11.50%, Deviation: 1.50%
neededClean
false
wordsTotal
200
wordsDialogue
23
99.9747%