reasoning benchmark
SWE-Lancer Leaderboard
SWE-Lancer is a benchmark of large language models on over 1,400 real-world freelance software engineering tasks from Upwork, valued at $1 million USD in total.
Updated Sep 5, 2026
Models4
Model coverage4
MetricScore
EvidenceB
SWE-Lancer Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Score66.30% | Percentile100.00% | Participants4 | EvidenceC | Evaluated |
| Rank02 | ModelOP | Score37.30% | Percentile66.67% | Participants4 | EvidenceC | Evaluated |
| Rank03 | ModelOP | Score32.60% | Percentile33.33% | Participants4 | EvidenceC | Evaluated |
| Rank04 | ModelOP | Score18.00% | Percentile0.00% | Participants4 | EvidenceC | Evaluated |
SWE-Lancer Highlights
The leading models and scores on this benchmark.
SWE-Lancer Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for SWE-Lancer
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is SWE-Lancer?
What SWE-Lancer measures and how its scores work.
SWE-Lancer includes independent engineering tasks graded via end-to-end tests and managerial tasks assessed against original engineering managers' choices.
It measures performance using the Score metric, reported as a ratio, across software engineering and managerial tasks.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- SWE-Lancer
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about SWE-Lancer.
Which model scores highest on SWE-Lancer?
GPT-5.1 Codex is currently ranked first with 66.30%.
What are the top three models on SWE-Lancer?
The current leaders are GPT-5.1 Codex (66.30%), GPT-4.5 (37.30%), and GPT-4o (32.60%).
Which SWE-Lancer model has the lowest official input price?
o3-mini has the lowest matched official input price at $1.1 input / $4.4 output per 1M tokens.
Which models are fastest among SWE-Lancer results?
The fastest matched records are GPT-4o (132.00 tok/s via OpenAI), o3-mini (115.00 tok/s via Azure), and GPT-5.1 Codex (50.00 tok/s via OpenAI).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.