reasoning benchmark
SWE-Bench Pro Leaderboard
SWE-Bench Pro is an advanced version of SWE-Bench that evaluates language models on complex, real-world software engineering tasks requiring extended reasoning and multi-step problem solving.
Updated Oct 23, 2026
Models63
Model coverage63
MetricScore
EvidenceB
SWE-Bench Pro Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Score89.90% | Percentile100.00% | Participants63 | EvidenceC | Evaluated |
| Rank02 | ModelAN | Score81.30% | Percentile98.39% | Participants63 | EvidenceC | Evaluated |
| Rank03 | ModelAN | Score80.00% | Percentile96.77% | Participants63 | EvidenceC | Evaluated |
| Rank04 | ModelAN | Score77.80% | Percentile95.16% | Participants63 | EvidenceC | Evaluated |
| Rank05 | ModelAN | Score69.20% | Percentile93.55% | Participants63 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score67.70% | Percentile91.94% | Participants63 | EvidenceC | Evaluated |
| Rank07 | ModelRA | Score66.10% | Percentile90.32% | Participants63 | EvidenceC | Evaluated |
| Rank08 | ModelTE | Score65.70% | Percentile88.71% | Participants63 | EvidenceC | Evaluated |
| Rank09 | ModelAN | Score64.80% | Percentile87.10% | Participants63 | EvidenceC | Evaluated |
| Rank10 | ModelXA | Score64.70% | Percentile85.48% | Participants63 | EvidenceC | Evaluated |
| Rank11 | ModelOP | Score64.60% | Percentile83.87% | Participants63 | EvidenceC | Evaluated |
| Rank12 | ModelAN | Score64.30% | Percentile82.26% | Participants63 | EvidenceC | Evaluated |
| Rank13 | ModelOP | Score63.40% | Percentile80.65% | Participants63 | EvidenceC | Evaluated |
| Rank14 | ModelAN | Score63.20% | Percentile79.03% | Participants63 | EvidenceC | Evaluated |
| Rank15 | ModelOP | Score62.70% | Percentile77.42% | Participants63 | EvidenceC | Evaluated |
| Rank16 | ModelAC | Score62.50% | Percentile75.81% | Participants63 | EvidenceC | Evaluated |
| Rank17 | ModelAC | Score62.50% | Percentile74.19% | Participants63 | EvidenceC | Evaluated |
| Rank18 | ModelZA | Score62.10% | Percentile72.58% | Participants63 | EvidenceC | Evaluated |
| Rank19 | ModelAC | Score61.70% | Percentile70.97% | Participants63 | EvidenceC | Evaluated |
| Rank20 | ModelME | Score61.50% | Percentile69.35% | Participants63 | EvidenceC | Evaluated |
| Rank21 | ModelAC | Score60.60% | Percentile67.74% | Participants63 | EvidenceC | Evaluated |
| Rank22 | ModelSA | Score59.60% | Percentile66.13% | Participants63 | EvidenceC | Evaluated |
| Rank23 | ModelPO | Score59.40% | Percentile64.52% | Participants63 | EvidenceC | Evaluated |
| Rank24 | ModelMI | Score59.00% | Percentile62.90% | Participants63 | EvidenceC | Evaluated |
| Rank25 | ModelGO | Score58.70% | Percentile61.29% | Participants63 | EvidenceC | Evaluated |
| Rank26 | ModelOP | Score58.60% | Percentile59.68% | Participants63 | EvidenceC | Evaluated |
| Rank27 | ModelMA | Score58.60% | Percentile58.06% | Participants63 | EvidenceC | Evaluated |
| Rank28 | ModelZA | Score58.40% | Percentile56.45% | Participants63 | EvidenceC | Evaluated |
| Rank29 | ModelTE | Score57.90% | Percentile54.84% | Participants63 | EvidenceC | Evaluated |
| Rank30 | ModelOP | Score57.70% | Percentile53.23% | Participants63 | EvidenceC | Evaluated |
SWE-Bench Pro Highlights
The leading models and scores on this benchmark.
SWE-Bench Pro Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for SWE-Bench Pro
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 Pro?
What SWE-Bench Pro measures and how its scores work.
SWE-Bench Pro is a reasoning benchmark for evaluating language models on software engineering tasks.
It measures performance on complex, real-world software engineering tasks requiring extended reasoning and multi-step problem solving, reported as Score in ratio units.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- SWE-Bench Pro
- 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 Pro.
Which model scores highest on SWE-Bench Pro?
Claude Opus 5.5 is currently ranked first with 89.90%.
What are the top three models on SWE-Bench Pro?
The current leaders are Claude Opus 5.5 (89.90%), Claude Sonnet 5.5 (81.30%), and Claude Fable 5 (80.00%).
Which SWE-Bench Pro model has the lowest official input price?
Claude Haiku 5.5 has the lowest matched official input price at $0.10 input / $0.50 output per 1M tokens.
Which models are fastest among SWE-Bench Pro results?
The fastest matched records are GPT-5.6 Luna (215.52 tok/s via OpenAI), MiniMax M2.5 (100.00 tok/s via MiniMax), and Gemini 3.1 Pro (90.00 tok/s via Google).
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.