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 Sep 5, 2026
Models55
Model coverage55
MetricScore
EvidenceB
SWE-Bench Pro Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Score80.00% | Percentile100.00% | Participants55 | EvidenceC | Evaluated |
| Rank02 | ModelAN | Score77.80% | Percentile98.15% | Participants55 | EvidenceC | Evaluated |
| Rank03 | ModelAN | Score69.20% | Percentile96.30% | Participants55 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score67.70% | Percentile94.44% | Participants55 | EvidenceC | Evaluated |
| Rank05 | ModelTE | Score65.70% | Percentile92.59% | Participants55 | EvidenceC | Evaluated |
| Rank06 | ModelXA | Score64.70% | Percentile90.74% | Participants55 | EvidenceC | Evaluated |
| Rank07 | ModelOP | Score64.60% | Percentile88.89% | Participants55 | EvidenceC | Evaluated |
| Rank08 | ModelAN | Score64.30% | Percentile87.04% | Participants55 | EvidenceC | Evaluated |
| Rank09 | ModelOP | Score63.40% | Percentile85.19% | Participants55 | EvidenceC | Evaluated |
| Rank10 | ModelAN | Score63.20% | Percentile83.33% | Participants55 | EvidenceC | Evaluated |
| Rank11 | ModelOP | Score62.70% | Percentile81.48% | Participants55 | EvidenceC | Evaluated |
| Rank12 | ModelAC | Score62.50% | Percentile79.63% | Participants55 | EvidenceC | Evaluated |
| Rank13 | ModelAC | Score62.50% | Percentile77.78% | Participants55 | EvidenceC | Evaluated |
| Rank14 | ModelZA | Score62.10% | Percentile75.93% | Participants55 | EvidenceC | Evaluated |
| Rank15 | ModelAC | Score61.70% | Percentile74.07% | Participants55 | EvidenceC | Evaluated |
| Rank16 | ModelME | Score61.50% | Percentile72.22% | Participants55 | EvidenceC | Evaluated |
| Rank17 | ModelAC | Score60.60% | Percentile70.37% | Participants55 | EvidenceC | Evaluated |
| Rank18 | ModelPO | Score59.40% | Percentile68.52% | Participants55 | EvidenceC | Evaluated |
| Rank19 | ModelMI | Score59.00% | Percentile66.67% | Participants55 | EvidenceC | Evaluated |
| Rank20 | ModelGO | Score58.70% | Percentile64.81% | Participants55 | EvidenceC | Evaluated |
| Rank21 | ModelOP | Score58.60% | Percentile62.96% | Participants55 | EvidenceC | Evaluated |
| Rank22 | ModelMA | Score58.60% | Percentile61.11% | Participants55 | EvidenceC | Evaluated |
| Rank23 | ModelZA | Score58.40% | Percentile59.26% | Participants55 | EvidenceC | Evaluated |
| Rank24 | ModelTE | Score57.90% | Percentile57.41% | Participants55 | EvidenceC | Evaluated |
| Rank25 | ModelOP | Score57.70% | Percentile55.56% | Participants55 | EvidenceC | Evaluated |
| Rank26 | ModelAC | Score57.60% | Percentile53.70% | Participants55 | EvidenceC | Evaluated |
| Rank27 | ModelBY | Score57.50% | Percentile51.85% | Participants55 | EvidenceC | Evaluated |
| Rank28 | ModelXI | Score57.20% | Percentile50.00% | Participants55 | EvidenceC | Evaluated |
| Rank29 | ModelBY | Score57.00% | Percentile48.15% | Participants55 | EvidenceC | Evaluated |
| Rank30 | ModelOP | Score56.80% | Percentile46.30% | Participants55 | 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 Fable 5 is currently ranked first with 80.00%.
What are the top three models on SWE-Bench Pro?
The current leaders are Claude Fable 5 (80.00%), Claude Mythos Preview (77.80%), and Claude Opus 4.8 (69.20%).
Which SWE-Bench Pro model has the lowest official input price?
MiMo-V2.5 has the lowest matched official input price at $0.14 input / $0.28 output per 1M tokens.
Which models are fastest among SWE-Bench Pro results?
The fastest matched records are Gemini 3.5 Flash (210.94 tok/s via Google), GPT-5.5 (134.94 tok/s via OpenAI), and GPT-5.4 nano (118.31 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.