LLM Reference
activeCoding

SWE-bench Pro

Metric: % Resolved (higher is better)Introduced: 2025

About

731-task multilingual real-world GitHub issue benchmark extending SWE-bench Verified with harder, more diverse tasks across Python, JavaScript, TypeScript, Java, Go, C++, and Rust.

How to read this benchmark

This benchmark uses a scoring system where higher is better. Scores are useful for directional filtering and model shortlisting, not for universal quality ranking.

Interpretation checklist: prefer benchmarks that are closest to your workload style, then validate against the linked model pages for pricing, context window, and provider availability.

Trust when:

  • There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
  • Model list covers the same version family you can actually deploy today.
  • Top candidates overlap with your required routing and feature requirements.

Don't trust when:

  • There is only one benchmark snapshot or the dataset appears stale.
  • Benchmark metric direction is opposite of your decision objective.
  • The score difference between options is narrow and likely within implementation variance.

Current modeled score band for tracked entries is roughly 69.2 – 58.6.

Window

May 20 to May 29

last 3 snapshots

Mean delta

-4.30

score points

Coverage

1

models in latest snapshot

Leaderboard preview (top 5)

  1. 1. Claude Opus 4.869.2
  2. 2. Claude Opus 4.764.3
  3. 3. Qwen3.7-Max60.6
  4. 4. GPT-5.558.6
  5. 5. Kimi K2.658.6