Introducing Three New Serverless Inference Providers: Hyperbolic, Nebius AI Studio, and Novita 🔥
•
100
Nebius
company
Verified
Inference Provider
VERIFIED
2,798,819 monthly requests
AI & ML interests
AI-centric cloud platform ready for intensive workloads Training-ready platform with NVIDIA® H100 Tensor Core GPUs. Competitive pricing. Dedicated support.
Recent Activity
View all activity
Articles
Could this dataset be repurposed for LLM training?
1
#7 opened about 22 hours ago
by
cppowboy
ibragim-bad
posted
an
update
14 days ago
Post
234
We tested Qwen3-Coder, GPT-5 and other 30+ models on new SWE-Bench like tasks from July 2025!
Hi all, I’m Ibragim from Nebius.
We ran a benchmark on 34 fresh GitHub PR tasks from July 2025 using the SWE-rebench leaderboard https://swe-rebench.com/leaderboard . These are real, recent problems — no training-set contamination — and include both proprietary and open-source models.
Quick takeaways:
> GPT-5-Medium leads overall (29.4% resolved rate, 38.2% pass@5).
> Qwen3-Coder is the best open-source performer, matching GPT-5-High in pass@5 (32.4%) despite a lower resolved rate.
> Claude Sonnet 4.0 lags behind in pass@5 at 23.5%.
All tasks come from the continuously updated, decontaminated nebius/SWE-rebench-leaderboard for real-world SWE tasks.
Hi all, I’m Ibragim from Nebius.
We ran a benchmark on 34 fresh GitHub PR tasks from July 2025 using the SWE-rebench leaderboard https://swe-rebench.com/leaderboard . These are real, recent problems — no training-set contamination — and include both proprietary and open-source models.
Quick takeaways:
> GPT-5-Medium leads overall (29.4% resolved rate, 38.2% pass@5).
> Qwen3-Coder is the best open-source performer, matching GPT-5-High in pass@5 (32.4%) despite a lower resolved rate.
> Claude Sonnet 4.0 lags behind in pass@5 at 23.5%.
All tasks come from the continuously updated, decontaminated nebius/SWE-rebench-leaderboard for real-world SWE tasks.
- 1 reply
Could you provide the Docker images?
9
#2 opened 3 months ago
by
lycfight
ibragim-bad
authored
a
paper
18 days ago
ibragim-bad
updated
a
dataset
18 days ago
How to build docker image for each instance?
2
#4 opened about 1 month ago
by
ludybupt
Any plans to release all of the Docker images for this dataset?
2
#5 opened 20 days ago
by
Paramecium880
ibragim-bad
updated
a
dataset
22 days ago
ibragim-bad
published
a
dataset
about 2 months ago
Add task category and library name to dataset card
#3 opened 3 months ago
by
nielsr
hr0nix
authored
a
paper
3 months ago
ibragim-bad
authored
a
paper
3 months ago
ibragim-bad
updated
a
dataset
3 months ago
ibragim-bad
published
a
dataset
4 months ago
Do you have the swe-bench harness code?
15
#2 opened 7 months ago
by
aidando73
ibragim-bad
updated
4
datasets
8 months ago