Hackernews posts about MMLU

1. iAsk Pro LLM achieves 93.89% on MMLU, beats GPT-4o and Claude 3.5 Sonnet (iask.ai)
   1 points by fariszr 20 days ago | discuss
2. Show HN: Open-source study to measure end user satisfaction levels with LLMs (open-llm-initiative.com)
   12 points by sparacha 25 days ago | 2 comments
3. McLuhan and Media Studies: An Underlooked Sub-Discipline? (www.austinatchley.xyz)
   2 points by prospector1065 25 days ago | discuss
4. Run FLUX.1 locally on your Mac (github.com)
   3 points by filipstrand 19 days ago | discuss
5. SHOW HN:A New 34B Open Source LLM, Astonishing 78 Score in MMLU (GPT-4 MMLU:83) (github.com)
   21 points by liuxiaopai 10 months ago | 5 comments
6. New medical LLM beats Med-PaLM-2, GPT-4 on MMLU benchmarks (huggingface.co)
   16 points by samjulien about 2 months ago | 2 comments
7. RedPajama-Incite-7B-Instruct Outperforms LLaMA on MMLU (twitter.com)
   9 points by vipulved about 1 year ago | 1 comments
8. SmartGPT: Major Benchmark Broken – 89.0% on MMLU and Exam Errors [video] (www.youtube.com)
   4 points by pps about 1 year ago | 5 comments
9. Errors in the MMLU: The Deep Learning Benchmark Is Wrong Surprisingly Often (derenrich.medium.com)
   3 points by kristianp 11 months ago | discuss
10. Death of MMLU? Revealing the Sensitivity and Instability of LLM Leaderboards (arxiv.org)
    2 points by hishamyahya 7 months ago | 1 comments
11. New Phi-3 Models (3B, 7B,14B), including 128k vision with impressive MMLU scores (twitter.com)
    2 points by brianjking 4 months ago | discuss
12. Tiny tweaks to tests like MMLU can shuffle model rankings (twitter.com)
    2 points by tosh 8 months ago | discuss
13. Yi-34B, 76.3 on MMLU, Apache 2.0 (huggingface.co)
    2 points by Leary 11 months ago | discuss
14. Errors in the MMLU: The Deep Learning Benchmark Is Wrong Surprisingly Often (derenrich.medium.com)
    2 points by brokensegue about 1 year ago | discuss
15. MMLU Benchmark (Multi-Task Language Understanding) (paperswithcode.com)
    2 points by ZeljkoS over 1 year ago | discuss
16. MMLU-Pro: Advanced edition of MMLU & new Leaderboard (huggingface.co)
    1 points by nopinsight 4 months ago | 1 comments
17. Gemini Benchmark – MMLU (compared with GPT-4-turbo, Mixtral) (hub.zenoml.com)
    1 points by zurfer 8 months ago | 1 comments
18. MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Bench (huggingface.co)
    1 points by Morinee 4 months ago | discuss
19. Multitask Language Understanding (MMLU) on Helm (crfm.stanford.edu)
    1 points by tosh 5 months ago | discuss
20. OLMo 1.7–7B: A 24 point improvement on MMLU (blog.allenai.org)
    1 points by tosh 5 months ago | discuss
21. MMLU Benchmark Broken (www.youtube.com)
    1 points by explosion-s about 1 year ago | discuss
22. The most widely used benchmarks for evaluating LLMs
    1 points by kavaivaleri 5 months ago | 1 comments
23. Are new LLM models trained on old benchmarks?
    1 points by rand0mwalk 3 months ago | discuss
24. Evaluation Platform for LLMs
    1 points by Dheemanthreddy 7 months ago | discuss
25. What's Going on with the Open LLM Leaderboard? (huggingface.co)
    40 points by tim_sw about 1 year ago | 2 comments
26. Overview of All Major LLM Benchmarks (www.confident-ai.com)
    1 points by 3d27 6 months ago | discuss
27. 789 KB Linux Without MMU on RISC-V (popovicu.com)
    166 points by yarapavan 12 months ago | 34 comments
28. Marshall McLuhan on surveillance and identity in the electric age (1977) [video] (twitter.com)
    108 points by llimos over 1 year ago | 32 comments
29. Marshall McLuhan explains the future of ads and the internet in 1966 (paleofuture.com)
    41 points by 082349872349872 over 1 year ago | 16 comments
30. MMU-less systems and FDPIC (maskray.me)
    39 points by todsacerdoti 7 months ago | 4 comments
31. Marshall McLuhan 1966 – Predicting the Internet [video] (www.youtube.com)
    13 points by type0 almost 2 years ago | 1 comments
32. My McLuhan Lecture on Enshittification (pluralistic.net)
    12 points by ojbyrne 7 months ago | 1 comments
33. My McLuhan Lecture on Enshittification (pluralistic.net)
    9 points by sssilver 7 months ago | 2 comments
34. Show HN: mlut – Atomic CSS toolkit with Sass and ergonomics (github.com)
    9 points by mr150 about 1 month ago | 1 comments