Benchmarks - DEV Community

Skip to content

DEV Community

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Nov 11

슈퍼클루 수학·과학 축은 38문항이었습니다: 점수 간격을 문항 수로 되돌리면 1위와 2위는 1문항 차

#ai #machinelearning #benchmarks #statistics

3 min read

InApp

Nov 11

16.4% hit #1 on the board, and my inference bill followed it up

#video #benchmarks #inferencecost #ai

1 min read

QuantID

Nov 9

Hugging Face Official Benchmarks: Daily Update 2026-11-10

#ai #benchmarks #huggingface #llm

4 min read

InApp

Nov 10

Why Inkling 2 Small's 30.6 needed a full video, not a leaderboard screenshot

#ai #benchmarks #evaluation #selfhosted

1 min read

Josep Oriol Carné

Nov 8

Metrics for Your AI Workers: Build a Personal Agent Benchmark

#ai #llm #agents #benchmarks

4 min read

InApp

Nov 8

Why an 88.64 leaderboard score needed the catch in the same sentence

#benchmarks #evals #video #ai

1 min read

ai maya

Nov 8

Inkling 2 Small is cheap per token but writes a lot: what 150,000 output tokens per task does to the price

#ai #machinelearning #llm #benchmarks

12 min read

InApp

Nov 8

Filming the Ripple-65B walkthrough taught me that 80.52 needs a table, not a take

#ai #benchmarks #video #selfhosted

1 min read

frank chu

Nov 8

23-point split: 6 models tied at 74% fell apart on 17 lines

#discuss #ai #machinelearning #benchmarks

5 min read

InApp

Nov 7

The 80.52 Short: why a 65B beating a 501B needed a video to be believed

#llm #benchmarks #video #ai

1 min read

MV2 (Munim, Inc.)

Nov 7

When strong models agree on a different GSM8K answer, the answer key is usually wrong

#machinelearning #datascience #nlp #benchmarks

3 min read

MV2 (Munim, Inc.)

Nov 7

How many wrong answer keys are left in MMLU?

#machinelearning #datascience #nlp #benchmarks

3 min read

김민식/학생

Nov 6

La misma molécula, otra GPU, otro puesto: cómo una tarjeta barata cambió un ranking sin dar ningún error

#ai #python #mlops #benchmarks

9 min read

MV2 (Munim, Inc.)

Nov 6

Our best shortcut for finding wrong MMLU answer keys failed its replication

#machinelearning #datascience #nlp #benchmarks

4 min read

InApp

Nov 6

The 89% Short: why a hallucination rate needed a video to be honest

#llmevals #benchmarks #hallucination #ai

1 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.