reasoning benchmark
SWE-Lancer (IC-Diamond subset)
SWE-Lancer (IC-Diamond subset) is a benchmark of real-world freelance software engineering tasks from Upwork, ranging from $50 bug fixes to $32,000 feature implementations. It evaluates AI models on independent engineering tasks using end-to-end tests triple-verified by experienced software engineers, and includes managerial tasks where models choose between technical implementation proposals.
Updated Aug 7, 2026
Published models6
Registry coverage6
MetricScore
EvidenceB
SWE-Lancer (IC-Diamond subset) leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | OP | 100.0% | 100.0% | 6 | C | |
| 2 | OP | 81.4% | 80.0% | 6 | C | |
| 3 | OP | 74.6% | 60.0% | 6 | C | |
| 4 | OP | 17.4% | 40.0% | 6 | C | |
| 5 | OP | 12.4% | 20.0% | 6 | C | |
| 6 | OP | 7.4% | 0.0% | 6 | C |
Score distribution
Top published rows on the benchmark's original scale.
SWE-Lancer (IC-Diamond subset) highlights
The top published results on this benchmark's own scale.
What is SWE-Lancer (IC-Diamond subset)?
Definition and scoring fields from the benchmark registry.
SWE-Lancer (IC-Diamond subset) is a benchmark of real-world freelance software engineering tasks from Upwork, ranging from $50 bug fixes to $32,000 feature implementations. It evaluates AI models on independent engineering tasks using end-to-end tests triple-verified by experienced software engineers, and includes managerial tasks where models choose between technical implementation proposals.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- SWE-Lancer (IC-Diamond subset)
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- swe-lancer-(ic-diamond-subset)|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about SWE-Lancer (IC-Diamond subset).
Which model scores highest on SWE-Lancer (IC-Diamond subset)?
GPT-5 is currently ranked first with 100.0%.
What does SWE-Lancer (IC-Diamond subset) measure?
SWE-Lancer (IC-Diamond subset) is a benchmark of real-world freelance software engineering tasks from Upwork, ranging from $50 bug fixes to $32,000 feature implementations. It evaluates AI models on independent engineering tasks using end-to-end tests triple-verified by experienced software engineers, and includes managerial tasks where models choose between technical implementation proposals.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
6 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.