Run: 2026-04-24-01KQ081SSZR6AQ2NQ22GHNYMBJ

Run Details

Model:
GPT-OSS 120B
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
6.2s
Cost:
$0.000472
Provider:
WandB

Evaluation summary

Score Evaluator
Details Link
100.00% Matches word count (details)

Model input

User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 10 words. Please make sure that each sentence has the same length. Only return the opening itself.

Model response

AI
Fog clung to the village street as midnight approached slowly. Detective Mara Ellis arrived, her trench coat dripping with rain. The chapel bell tolled, echoing over cobblestones, announcing tragedy tonight. A scream shattered silence, drawing townsfolk toward the looming manor. Inside, a chandelier swayed above a lifeless body, bloodied floor. Mara knelt, eyes scanning clues, heart racing with anticipation deeply.
created_at"2026-04-24T17:19:26.541Z" 4/24/2026, 5:19:26 PM
model"openai/gpt-oss-120b"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency272
moderation_latency(null)
generation_time5632
tokens_prompt46
tokens_completion789
native_tokens_prompt100
native_tokens_completion762
native_tokens_completion_images(null)
native_tokens_reasoning678
native_tokens_cached32
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
num_fetches(null)
web_search_engine(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.0004722
router(null)
provider_responses
0
endpoint_id"3ca6292f-cef7-48a2-bf52-988e934cab57"
id"chatcmpl-853b2bd764fe0b5b"
is_byokfalse
latency221
model_permaslug"openai/gpt-oss-120b"
provider_name"WandB"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer(null)
request_id"req-1777051166-WDZhIG3rP0iRkOOuOkHx"
session_id(null)
api_type"completions"
id"gen-1777051166-MFhUf6FU6rp661LBdWUV"
upstream_id"chatcmpl-853b2bd764fe0b5b"
total_cost0.0004722
cache_discount(null)
upstream_inference_cost0
provider_name"WandB"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Matches word count n/a
neededCleanfalse
sentences6
wordCounts
010
110
210
310
410
510