reasoning benchmark
SWE-bench Verified (Agentless) Leaderboard
SWE-bench Verified (Agentless) is a human-validated subset of SWE-bench that evaluates language models on resolving real-world GitHub issues using an agentless approach.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
SWE-bench Verified (Agentless) Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMA | Score51.80% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelXI | Score35.70% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
SWE-bench Verified (Agentless) Highlights
The leading models and scores on this benchmark.
SWE-bench Verified (Agentless) Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for SWE-bench Verified (Agentless)
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is SWE-bench Verified (Agentless)?
What SWE-bench Verified (Agentless) measures and how its scores work.
A human-validated benchmark subset for evaluating language models on software engineering problems from real-world GitHub issues.
It measures models' ability to understand and coordinate changes across multiple functions, classes, and files simultaneously, reported as a Score ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- SWE-bench Verified (Agentless)
- 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-bench Verified (Agentless).
Which model scores highest on SWE-bench Verified (Agentless)?
Kimi K2 Instruct is currently ranked first with 51.80%.
What are the top three models on SWE-bench Verified (Agentless)?
The current leaders are Kimi K2 Instruct (51.80%) and MiMo-V2.5-Pro (35.70%).
Which SWE-bench Verified (Agentless) model has the lowest official input price?
MiMo-V2.5-Pro has the lowest matched official input price at $0.44 input / $0.87 output per 1M tokens.
Which models are fastest among SWE-bench Verified (Agentless) results?
The fastest matched records are MiMo-V2.5-Pro (5.27 tok/s via DeepInfra).
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.