SWE-Lancer
Current 198-task offline patch benchmark derived from paid Upwork work, with historical mixed implementation and manager-task variants.
The maintained leaderboard is frozen at July 2025 and narrows paper-era Diamond from 502 mixed tasks to 198 offline IC tasks, making unlabeled Diamond claims non-comparable.
Performance Timeline
Longitudinal progression of model scores against human baselines.Performance & Historical Trajectory
Empirical score progression across model release dates and evaluation rounds.
Human Baseline & Difficulty Horizon
Calibrated human reference points, specialist benchmarks, and ceiling thresholds.Commercial freelance software engineers completing real-world Upwork software engineering milestones.
Metric & Scoring Methodology
Verification protocols, aggregation formulas, and specialized metric variants.pass@1 accuracy on the 198-task Diamond offline subset (%)Dataset & Compute Cost
Evaluation volume, public availability, API pricing, and local hardware requirements.$5 – $20 USD for full benchmark evaluation run on frontier APIs.
1x NVIDIA RTX 4090 (24GB) or A100 (40GB/80GB) via vLLM / SGLang
How to Run & Reproduce
Standardized evaluation protocols, CLI commands, and reproducible runner templates.lm_eval --model hf --model_args pretrained=<model_path> --tasks swe-lancer --batch_size autoopencompass --datasets swe-lancer --models <model_config># Standard API Evaluation Loop
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": prompt}],
temperature=0.0,
)When publishing results for SWE-Lancer, always report the exact prompt template, few-shot exemplar ordering, sampling temperature (temperature=0), maximum reasoning budget tokens, and the precise timestamped model snapshot ID.
Contamination & Memorization Analysis
Audit of pretraining exposure risks, memorization vectors, and refresh policies.Static fixed snapshot
Public on web / HuggingFace