Hackernews posts about MMLU

1. Diffusion LLM may make most of the AI engineering stack obsolete
   3 points by victorpiles99 27 days ago | discuss
2. ARCHE3-7B – Sparse Moe with SmartRouter and Foundation Curriculum Training
   1 points by OpenSynapseLabs 4 days ago | discuss
3. Malus – Clean Room as a Service (malus.sh)
   1433 points by microflash 26 days ago | 531 comments
4. "Malus": Is Copyleft Dead? (heathermeeker.com)
   4 points by Tomte 19 days ago | discuss
5. "Malus": Is Copyleft Dead? (heathermeeker.com)
   2 points by CharlesW 18 days ago | discuss
6. "Malus": Is Copyleft Dead? (heathermeeker.com)
   2 points by Tomte 21 days ago | discuss
7. Show HN: Cadenza – Connect Wandb logs to agents easily for autonomous research (github.com)
   3 points by hgarud 3 days ago | discuss
8. Ask HN: Build trust for closed source product
   1 points by vitalikpie 12 days ago | 5 comments
9. The changing goalposts of AGI and timelines (mlumiste.com)
   404 points by skandium 30 days ago | 388 comments
10. I Saw Something New in San Francisco (www.nytimes.com)
    7 points by droidjj 9 days ago | discuss
11. Ask HN: Is it feasible to build an ESP32 emulator in JavaScript? (github.com)
    5 points by dmonterocrespo 16 days ago | 6 comments
12. I Saw Something New in San Francisco (www.nytimes.com)
    4 points by platzhirsch 6 days ago | 2 comments
13. I Saw Something New in San Francisco (www.nytimes.com)
    4 points by zacharyozer 9 days ago | discuss
14. I Saw Something New in San Francisco (By Ezra Klein) (www.nytimes.com)
    3 points by sebmellen 2 days ago | 1 comments
15. Clean Room as a Service (malus.sh)
    3 points by Venn1 26 days ago | discuss
16. The quiet obsolescence of generosity, and a commercial alternative (malus.sh)
    2 points by dTal 21 days ago | 1 comments
17. Show HN: Connect your research data easily to AI agents (myluca.ai)
    1 points by hgarud 29 days ago | discuss
18. Composo open-sources its LLM-as-Judge technique (83.6% on RewardBench 2) (github.com)
    5 points by mlukewizard 5 days ago | discuss
19. Show HN: Shrouded, secure memory management in Rust (github.com)
    5 points by mhluongo 15 days ago | discuss
20. Payment Required and x402 and how to set it up (matija.eu)
    1 points by mmunj 15 days ago | discuss
21. Claude Code reverse-engineered itself. Two subagents refused. It called them shy (www.skelpo.com)
    3 points by amlug 20 days ago | 1 comments
22. Show HN: EasyShot – macOS screenshot thumbnails that don't disappear after 5s
    1 points by amlug 19 days ago | 3 comments
23. Show HN: Mango – A native, open-source MongoDB GUI. 7 MB, no Electron (mangoquery.com)
    1 points by amlug 5 days ago | discuss
24. New medical LLM beats Med-PaLM-2, GPT-4 on MMLU benchmarks (huggingface.co)
    16 points by samjulien over 1 year ago | 2 comments
25. Show HN: Run MMLU benchmark on any LLM endpoint (mmlu.borgcloud.ai)
    2 points by lostmsu 11 months ago | discuss
26. LLM Comparison/Test: 25 SOTA LLMs (Including QwQ) Through 59 MMLU-Pro CS Runs (huggingface.co)
    2 points by ororm over 1 year ago | discuss
27. Multilingual MMLU Dataset from OpenAI (OpenAI/Mmmlu) (huggingface.co)
    2 points by ekojs over 1 year ago | discuss
28. New Phi-3 Models (3B, 7B,14B), including 128k vision with impressive MMLU scores (twitter.com)
    2 points by brianjking almost 2 years ago | discuss
29. Graph-based multi-agents smash long-context benchmarks–89% MMLU-Pro on 8B models (github.com)
    1 points by FeelTheAGI2 about 2 months ago | 1 comments
30. MMLU-Pro: Advanced edition of MMLU & new Leaderboard (huggingface.co)
    1 points by nopinsight almost 2 years ago | 1 comments
31. iAsk Pro LLM achieves 93.89% on MMLU, beats GPT-4o and Claude 3.5 Sonnet (iask.ai)
    1 points by fariszr over 1 year ago | discuss
32. MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Bench (huggingface.co)
    1 points by Morinee almost 2 years ago | discuss
33. Multitask Language Understanding (MMLU) on Helm (crfm.stanford.edu)
    1 points by tosh almost 2 years ago | discuss
34. OLMo 1.7–7B: A 24 point improvement on MMLU (blog.allenai.org)
    1 points by tosh almost 2 years ago | discuss
35. Show HN: AutoThink – Boosts local LLM performance with adaptive reasoning
    397 points by codelion 10 months ago | 68 comments
36. Show HN: Arch-Router – 1.5B model for LLM routing by preferences, not benchmarks
    66 points by adilhafeez 9 months ago | 15 comments
37. Show HN: BenchFlow – run AI benchmarks as an API (github.com)
    24 points by xdotli about 1 year ago | 1 comments
38. Show HN: QwQ-32B APIs – o1 like reasoning at 1% the cost
    17 points by ozgune about 1 year ago | 3 comments
39. Show HN: Open-source study to measure end user satisfaction levels with LLMs (open-llm-initiative.com)
    12 points by sparacha over 1 year ago | 2 comments
40. LLM Benchmark: Frontier models now statistically indistinguishable
    7 points by js4ever 4 months ago | 4 comments
41. Show HN: I built the LLM Comparison Tool I wish existed (llm-stats.com)
    7 points by JonathanChavez over 1 year ago | 3 comments
42. Show HN: Claude Code 2.0 router – preference-aligned routing to multiple LLMs (github.com)
    4 points by adilhafeez 6 months ago | 1 comments
43. Show HN: Forecaster Arena – Testing LLMs on real events with prediction markets (forecasterarena.com)
    4 points by setrf 4 months ago | discuss
44. Show HN: 1.5B LLM routing model that aligns to preferences, not leaderboards (huggingface.co)
    4 points by honorable_coder 9 months ago | discuss
45. Show HN: MALLM – A Multi-Agent Framework for Task Solving (github.com)
    4 points by jpwahle 9 months ago | discuss
46. Show HN: Model-literals, model-aliases, and preference-aligned routing for LLMs (docs.archgw.com)
    2 points by honorable_coder 7 months ago | discuss
47. Show HN: LLM Benchmarking Suite (github.com)
    2 points by Dhyaneesh about 1 year ago | discuss
48. Show HN: OptiLLMBench – Test how inference optimization tricks scale up LLMs
    2 points by codelion about 1 year ago | discuss
49. Show HN: AIBenchy – Independent AI Leaderboard (aibenchy.com)
    1 points by XCSme about 2 months ago | 1 comments
50. Show HN: MarginDash – See which AI customers are profitable (margindash.com)
    1 points by gdhaliwal23 about 2 months ago | 1 comments
51. Show HN: MarginDash – See which AI customers are profitable (margindash.com)
    1 points by gdhaliwal23 about 2 months ago | 1 comments
52. Ask HN: Are LLMs getting better, how can you tell?
    1 points by ahamilton454 about 1 year ago | 1 comments
53. The most widely used benchmarks for evaluating LLMs
    1 points by kavaivaleri almost 2 years ago | 1 comments