I am reading this right, is this model way better than Gemma 3n[1]? (For only the benchmarks that are common among the models)
=====
LiveCodeBench
E4B IT: 13.2
Qwen: 55.2
===== AIME25
E4B IT: 11.6
Qwen: 81.3
Qwen3-4B-Thinking-2507
11–20 of 64 posts
Re: Qwen3-4B-Thinking-2507
#12Earlier quoted context omitted.
https://artificialanalysis.ai/leaderboards/models?open_weigh...
Compare these rankings to actual usage: https://openrouter.ai/rankings Claude is not cheap, why is it far and away the most popular if it's not top 10 in performance? Qwen3 235b ranks highest on these benchmarks among open models, but I have never met someone who prefers its output over Deepseek R1. It's extremely wordy and often gets caught in thought loops. My interpretation is that the models at the top of Artific…
Thanks for sharing that. Interesting that the leaderboard is dominated by Anthropic, Google and DeepSeek. Openai doesn't even register.
Re: Qwen3-4B-Thinking-2507
#13This one should work on personal computers! I'm thankful for Chinese companies raising the floor.
[flagged]
Re: Qwen3-4B-Thinking-2507
#14Is there a crowd-sourced sentiment score for models? I know all these scores are juiced like crazy. I stopped taking them at face value months ago. What I want to know is if other folks out there actually use them or if they are unreliable.
Re: Qwen3-4B-Thinking-2507
#15This one should work on personal computers! I'm thankful for Chinese companies raising the floor.
[flagged]
I’m American. Just giving some background to the feeling. There’s some discontent with some western communities (localllama) that Chinese developers have been open weighting all of their models while most western models have been closed weights.
Re: Qwen3-4B-Thinking-2507
#16This one should work on personal computers! I'm thankful for Chinese companies raising the floor.
[flagged]
Let's say any country create the most powerful - and thus best - LLMs. They over time infiltrate it with their political will. Over 20-30 years, I'd imagine people asking those LLMs will have their minds' shifted.
But. That's just me, my pessimism-sci-fi scenario.
Re: Qwen3-4B-Thinking-2507
#17Is there a crowd-sourced sentiment score for models? I know all these scores are juiced like crazy. I stopped taking them at face value months ago. What I want to know is if other folks out there actually use them or if they are unreliable.
This has been around for a while https://lmarena.ai/leaderboard/text/coding
Re: Qwen3-4B-Thinking-2507
#18Is there a crowd-sourced sentiment score for models? I know all these scores are juiced like crazy. I stopped taking them at face value months ago. What I want to know is if other folks out there actually use them or if they are unreliable.
openrouter usage stats
Re: Qwen3-4B-Thinking-2507
#19So this 4B dense model gets very similar performance to the 30B MoE variant with 7.5x smaller footprint.
It gets similar performance to the old version of the 30B MoE model, but not the updated version. https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507
Re: Qwen3-4B-Thinking-2507
#20Is there a crowd-sourced sentiment score for models? I know all these scores are juiced like crazy. I stopped taking them at face value months ago. What I want to know is if other folks out there actually use them or if they are unreliable.
openrouter usage stats
https://openrouter.ai/rankings
The new qwen3 model is not out yet.