Run: 2026-09-03-01M1KC9MFZ9MX4NKFCFHV27A23

Run Details

Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
Data extraction
Scenario:
Highest-rated movie
Duration:
2.2s
Cost:
$0.000285
Provider:
Novita

Evaluation summary

Score Evaluator
Details Link
Pass Matches text (details)
Pass Matches Regex (details)
no eval Overall

Model input

User/Human
What is the title of the highest-rated movie? Only return the movie title, preserving its original capitalization. Movie Ratings: - The Shawshank Redemption (1994): 9.3/10 - The Godfather (1972): 9.2/10 - 12 Angry Men (1957): 8.9/10 - Schindler's List (1993): 9.0/10 - The Lord of the Rings: The Return of the King (2003): 9.0/10

Model response

AI
The Shawshank Redemption
created_at"2026-09-03T10:16:09.999Z" 9/3/2026, 10:16:09 AM
model"deepseek/deepseek-v4-pro-20260813"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1295
moderation_latency(null)
generation_time2168
tokens_prompt85
tokens_completion50
native_tokens_prompt196
native_tokens_completion45
native_tokens_completion_images(null)
native_tokens_reasoning38
native_tokens_cached128
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"
service_tier(null)
usage0.000284856
router(null)
user_agent"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer(null)
request_id"req-1788430569-HZD9l3Cre3vaW9Syst1N"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1788430569-zqjvBfWIVgp36x4YCDxp"
upstream_id"572f15d8a2b504fef90c686d3d810e88"
provider_responses
0
endpoint_id"46f2098d-3994-4c59-b3f9-cbbbf44a2f45"
id"572f15d8a2b504fef90c686d3d810e88"
is_byokfalse
latency431
model_permaslug"deepseek/deepseek-v4-pro-20260813"
provider_name"Novita"
status200
total_cost0.000284856
cache_discount0.000152064
upstream_inference_cost0
provider_name"Novita"
response_cache_source_id(null)
data_region"global"
workspace_id"97e315e5-d303-487d-83c1-83180e8a13d4"

Evaluation details

Result Evaluator Details Meta Data
Pass Matches text
Case sensitive: The Shawshank Redemption
 n/a
Pass Matches Regex
/\bThe Shawshank Redemption\b/
 n/a
no eval