Longtail-SWE is a benchmark of issue-resolution tasks designed to evaluate coding agents across 13 underrepresented programming languages.
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
Papers
Interpreting Coding Agents Through Their Behavioral Trajectories
Longtail-SWE: High-Quality SWE Tasks for Underrepresented Languages
Organization Card
Welcome to Nebius!
Visit us at https://nebius.com/.
models 10
nebius/EAGLE3-Llama-3.1-8B-Instruct
Text Generation • 0.4B • Updated • 216
nebius/EAGLE3-Qwen3-235B-A22B-Instruct-2507
Text Generation • 0.6B • Updated • 651
nebius/EAGLE3-gpt-oss-120b
Text Generation • 0.4B • Updated • 156
nebius/EAGLE3-Llama-3.3-70B-Instruct
Text Generation • 1B • Updated • 706
nebius/EAGLE3-gpt-oss-20b
Text Generation • 0.4B • Updated • 807
nebius/MLP-Speculator-Llama-3.1-8B-Instruct
Text Generation • 0.2B • Updated • 64
nebius/MEDUSA-Llama-3.1-8B-Instruct
Text Generation • 3B • Updated • 66
nebius/MTP-DeepSeek-V3-0324
Text Generation • 13B • Updated • 169 • 3
nebius/SWE-rebench-openhands-Qwen3-235B-A22B
Text Generation • 235B • Updated • 23 • 8
nebius/SWE-rebench-openhands-Qwen3-30B-A3B
Text Generation • 31B • Updated • 239 • 12
datasets 16
nebius/Longtail-SWE-trajectories
Viewer • Updated • 6.67k • 462 • 2
nebius/Longtail-SWE
Viewer • Updated • 471 • 751 • 4
nebius/SWE-rebench-leaderboard-trajectories
Viewer • Updated • 27.3k • 5
nebius/SWE-rebench-V2
Viewer • Updated • 32.1k • 128k • 76
nebius/SWE-rebench-V2-PRs
Viewer • Updated • 126k • 67.4k • 19
nebius/SWE-rebench-leaderboard
Viewer • Updated • 1.72k • 7.61k • 30
nebius/DeepSeek-V3-Infinity-Instruct-0625
Viewer • Updated • 660k • 202 • 3
nebius/Qwen3-235B-Instruct-Infinity-Instruct-0625
Viewer • Updated • 660k • 336 • 3
nebius/gpt-oss-120b-Infinity-Instruct-0625
Viewer • Updated • 659k • 226 • 1
nebius/gpt-oss-20b-Infinity-Instruct-0625
Viewer • Updated • 660k • 204