backend
Datasets
All datasets matching “backend”card_backend
Eval Cards Backend Dataset
Pre-computed evaluation data powering the Eval Cards frontend.
Generated by the eval-cards backend pipeline.
Last generated: 2026-05-05T11:30:42.961096Z
Quick Stats
Stat
Value
Models
5,678
Evaluations (benchmarks)
798
Metric-level evaluations
1321
Source configs processed
52
Benchmark metadata cards
240
File Structure
.
├── README.md # This file
├── manifest.json… See the full description on the dataset page: https://huggingface.co/datasets/evaleval/card_backend.omnimcp_python_backend_architect_teaser
🚀 OmniMCP: Python Backend Architect (Evaluation Teaser Edition)
🛡️ DON'T WANT TO TRAIN RAW DATASETS? RUN IT IN CURSOR & CLAUDE TODAY!
You don't need A100 GPUs, Axolotl, or complex Unsloth fine-tuning. This package now includes a Turnkey Ready-to-Run Model Context Protocol (MCP) Server that plugs directly into Cursor IDE and Claude Desktop with 1-click!
⚡ What the Turnkey MCP Guard does inside Cursor & Claude in <100ms:
🩺 Instant Traceback Diagnosis: Feed any… See the full description on the dataset page: https://huggingface.co/datasets/emgena/omnimcp_python_backend_architect_teaser.backendbench_tests
TorchBench
The TorchBench suite of BackendBench is designed to mimic real-world use cases. It provides operators and inputs derived from 155 model traces found in TIMM (67), Hugging Face Transformers (45), and TorchBench (43). (These are also the models PyTorch developers use to validate performance.) You can view the origin of these traces by switching the subset in the dataset viewer to ops_traces_models and torchbench for the full dataset.
When running BackendBench, much of the… See the full description on the dataset page: https://huggingface.co/datasets/GPUMODE/backendbench_tests.requestsresultstemp_evalcard_backend
Eval Cards Backend Dataset
Pre-computed evaluation data powering the Eval Cards frontend.
Generated by the eval-cards backend pipeline.
Last generated: 2026-04-29T01:12:58.765261Z
Quick Stats
Stat
Value
Models
5,829
Evaluations (benchmarks)
581
Metric-level evaluations
1092
Source configs processed
34
Benchmark metadata cards
85
File Structure
.
├── README.md # This file
├── manifest.json #… See the full description on the dataset page: https://huggingface.co/datasets/j-chim/temp_evalcard_backend.
