nebius/SWE-rebench-openhands-trajectories
Viewer
•
Updated
•
67.1k
•
388
•
98
Nebius
company
Verified
Inference Provider
VERIFIED
3,636,706 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
vim-ary
updated
a
dataset
7 days ago
Exactly what I have been looking for.
❤️
1
1
#1 opened 10 days ago
by
leonletto
ibragim-bad
updated
2
datasets
10 days ago
ibragim-bad
posted
an
update
10 days ago
Post
323
🎄 67,074 Qwen3-Coder OpenHands trajectories + 2 RFT checkpoints.
We release: 67,000+ trajectories from 3,800 resolved issues in 1,800+ Python repos.
About 3x more successful trajectories and 1.5x more repos than our previous dataset.
Trajectories are long: on average 64 turns, up to 100 turns and 131k context length.
> RFT on this data, SWE-bench Verified:
Qwen3-30B-Instruct: 25.7% → 50.3% Pass@1.
Qwen3-235B-Instruct: 46.2% → 61.7% Pass@1.
Also strong gains on SWE-rebench September.
> We also did massive evals.
We run OpenHands with 100 and 500 turns.
We compare models under both limits.
We run on SWE-bench Verified and several months of SWE-rebench.
!!! We also check tests written by the models.
We measure how often tests are correct.
We check how often the final patch passes its own tests.
This gives a pool of tests for verifiers and auto graders.
> Fully permissive licenses
Dataset and models: https://huggingface.co/collections/nebius/openhands-trajectories
Blog post: https://nebius.ai/blog/posts/openhands-trajectories-with-qwen3-instruct
We release: 67,000+ trajectories from 3,800 resolved issues in 1,800+ Python repos.
About 3x more successful trajectories and 1.5x more repos than our previous dataset.
Trajectories are long: on average 64 turns, up to 100 turns and 131k context length.
> RFT on this data, SWE-bench Verified:
Qwen3-30B-Instruct: 25.7% → 50.3% Pass@1.
Qwen3-235B-Instruct: 46.2% → 61.7% Pass@1.
Also strong gains on SWE-rebench September.
> We also did massive evals.
We run OpenHands with 100 and 500 turns.
We compare models under both limits.
We run on SWE-bench Verified and several months of SWE-rebench.
!!! We also check tests written by the models.
We measure how often tests are correct.
We check how often the final patch passes its own tests.
This gives a pool of tests for verifiers and auto graders.
> Fully permissive licenses
Dataset and models: https://huggingface.co/collections/nebius/openhands-trajectories
Blog post: https://nebius.ai/blog/posts/openhands-trajectories-with-qwen3-instruct
- 2 replies
djalexj
updated
a
model
11 days ago
ibragim-bad
published
2
models
11 days ago
ibragim-bad
updated
2
models
11 days ago
ibragim-bad
updated
a
dataset
11 days ago
vim-ary
updated
2
models
28 days ago
vim-ary
updated
a
collection
about 1 month ago
Repo logs and caching price
3
#2 opened about 2 months ago
by
blazespinnaker
How can I find all instance_ids that come with a Docker image?
4
#10 opened 2 months ago
by
KYLN24
mrshevan
authored
a
paper
5 months ago