DeepSeek-v3.1
api-docs.deepseek.com
DeepSeek-v3.1
1–10 of 273 posts
Re: DeepSeek-v3.1
#2For reference, here is the terminal-bench leaderboard:
https://www.tbench.ai/leaderboard
Looks like it doesn't get close to GPT-5, Claude 4, or GLM-4.5, but still does reasonably well compared to other open weight models. Benchmarks are rarely the full story though, so time will tell how good it is in practice.
Re: DeepSeek-v3.1
#3It's a hybrid reasoning model. It's good with tool calls and doesn't think too much about everything, but it regularly uses outdated tool formats randomly instead of the standard JSON format. I guess the V3 training set has a lot of those.
Re: DeepSeek-v3.1
#4For reference, here is the terminal-bench leaderboard: https://www.tbench.ai/leaderboard Looks like it doesn't get close to GPT-5, Claude 4, or GLM-4.5, but still does reasonably well compared to other open weight models. Benchmarks are rarely the full story though, so time will tell how good it is in practice.
The DeepSeek R1 in that list is the old model that's been replaced.
Update: Understood.
Re: DeepSeek-v3.1
#5It seems behind Qwen3 235B 2507 Reasoning (which I like) and gpt-oss-120B:
https://artificialanalysis.ai/models/deepseek-v3-1-reasoning
Re: DeepSeek-v3.1
#6It seems behind Qwen3 235B 2507 Reasoning (which I like) and gpt-oss-120B: https://artificialanalysis.ai/models/deepseek-v3-1-reasoning Pricing: https://openrouter.ai/deepseek/deepseek-chat-v3.1
Those Qwen3 2507 models are the local creme-de-la-creme right now. If you've got any sort of GPU and ~32gb of RAM to play with, the A3B one is great for pair-programming tasks.
Re: DeepSeek-v3.1
#7For reference, here is the terminal-bench leaderboard: https://www.tbench.ai/leaderboard Looks like it doesn't get close to GPT-5, Claude 4, or GLM-4.5, but still does reasonably well compared to other open weight models. Benchmarks are rarely the full story though, so time will tell how good it is in practice.
My personal experience is that it produces high quality results.
Re: DeepSeek-v3.1
#8It seems behind Qwen3 235B 2507 Reasoning (which I like) and gpt-oss-120B: https://artificialanalysis.ai/models/deepseek-v3-1-reasoning Pricing: https://openrouter.ai/deepseek/deepseek-chat-v3.1
Those Qwen3 2507 models are the local creme-de-la-creme right now. If you've got any sort of GPU and ~32gb of RAM to play with, the A3B one is great for pair-programming tasks.
Do you happen to know if it can be run via an eGPU enclosure with f.ex. RTX 5090 inside, under Linux?
I'm considering buying a Linux workstation lately and I want it full AMD. But if I can just plug an NVIDIA card via an eGPU card for self-hosting LLMs then that would be amazing.
Re: DeepSeek-v3.1
#9For reference, here is the terminal-bench leaderboard: https://www.tbench.ai/leaderboard Looks like it doesn't get close to GPT-5, Claude 4, or GLM-4.5, but still does reasonably well compared to other open weight models. Benchmarks are rarely the full story though, so time will tell how good it is in practice.
My personal experience is that it produces high quality results.
Any example or prompt you use to make this statment?
Re: DeepSeek-v3.1
#10For reference, here is the terminal-bench leaderboard: https://www.tbench.ai/leaderboard Looks like it doesn't get close to GPT-5, Claude 4, or GLM-4.5, but still does reasonably well compared to other open weight models. Benchmarks are rarely the full story though, so time will tell how good it is in practice.
The DeepSeek R1 in that list is the old model that's been replaced. Update: Understood.
Yes, and 31.3% is given in the announcement as the performance of the new v3.1, which would put it in sixteenth place.