agents benchmark
APEX-SWE Leaderboard
APEX-SWE evaluates AI agents on software engineering tasks requiring multi-step coding, debugging, and verification.
Updated Sep 5, 2026
Models1
Model coverage1
MetricScore
EvidenceB
APEX-SWE Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelXA | Score56.40% | Percentile100.00% | Participants1 | EvidenceC | Evaluated |
APEX-SWE Highlights
The leading models and scores on this benchmark.
The Top AI Models for APEX-SWE
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis apex-swe AI model leaderboard uses descending score in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01XAxAI
- Score
- 56.40%
- Price
- $2.0 input / $6.0 output per 1M tokens
- Speed
- Up to 132.69 tok/s via xAI
Strengths
- Ranks #1 of 1 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures APEX-SWE, not total model capability
Selection summary
Best AI Models for APEX-SWE
Grok 4.6 currently leads APEX-SWE with 56.40%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is APEX-SWE?
What APEX-SWE measures and how its scores work.
APEX-SWE is a benchmark for AI agents on software engineering tasks.
It measures performance on tasks requiring multi-step coding, debugging, and verification, reported as a Score ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- APEX-SWE
- Modality
- text
- Primary category
- agents
- 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 APEX-SWE.
Which model scores highest on APEX-SWE?
Grok 4.6 is currently ranked first with 56.40%.
What are the top three models on APEX-SWE?
The current leaders are Grok 4.6 (56.40%).
Which APEX-SWE model has the lowest official input price?
Grok 4.6 has the lowest matched official input price at $2.0 input / $6.0 output per 1M tokens.
Which models are fastest among APEX-SWE results?
The fastest matched records are Grok 4.6 (132.69 tok/s via xAI).
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.