AI Models & LLM Benchmark Tracker
Pricing
from $5.00 / 1,000 results
AI Models & LLM Benchmark Tracker
Scrapes and consolidates live LLM leaderboard benchmarks, Arena Elo ratings, MMLU, and HumanEval scores into structured JSON/CSV datasets.
AI Models & LLM Benchmark Tracker
Pricing
from $5.00 / 1,000 results
Scrapes and consolidates live LLM leaderboard benchmarks, Arena Elo ratings, MMLU, and HumanEval scores into structured JSON/CSV datasets.
model_name
Optional
Name of the AI frontier or open-source model
organization
Optional
Lab or organization that created the model
arena_elo
Optional
LMSYS Chatbot Arena Elo rating
coding_score
Optional
HumanEval / Python coding benchmark percentage
mmlu_score
Optional
MMLU general reasoning accuracy score
math_score
Optional
MATH benchmark accuracy score
license
Optional
License type: open-source or proprietary
parameters_billion
Optional
Total model parameters in billions
context_window
Optional
Maximum context window length in tokens
data_source
Optional
Source leaderboard of origin
scraped_at
Optional
UTC ISO timestamp when data was scraped