BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases7

SWE Atlas: Refactoring leaderboard

As of 6 Nov 2026, the top score on SWE Atlas: Refactoring is 59.0% by GPT-6 Astra (OpenAI), ahead of Claude Fable 5.1 at 56.7%, across 17 model configurations with a published result (Scale AI SEAL, result dated 9 Sep 2026). Multi-file refactors in real repositories, checked by tests and review criteria. SWE Atlas: Refactoring is shown for reference only and does not count toward the BenchLeader Index.

Key facts (as of 6 Nov 2026)

  • GPT-6 Astra holds the top SWE Atlas: Refactoring score at 59.0% (Scale AI SEAL, 9 Sep 2026).
  • Claude Fable 5.1 is second on SWE Atlas: Refactoring at 56.7% (Scale AI SEAL, 2 Sep 2026).
  • SWE Atlas: Refactoring: Refactoring tasks in real repositories. Scale AI (Scale AI SEAL).
  • 17 model configurations have a published SWE Atlas: Refactoring result on BenchLeader (BenchLeader, 6 Nov 2026).
  • SWE Atlas: Refactoring does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).

Refactoring tasks in real repositories. Scale AI.

Published by
Scale AI SEAL
Category
Coding
Index weight
Reference only
Models
17
Data as of
6 Nov 2026

Scale AI SEAL Leaderboards.

What the test looks like

Multi-file refactors in real repositories, checked by tests and review criteria.

How it is scored

Percent of refactors accepted, published by Scale AI.

What to keep in mind

Harness-dependent, like all agentic coding boards.

Top 15
  1. 1GPT-6 Astra (xhigh)59.0%
  2. 2Claude Fable 5.1 (xhigh)56.7%
  3. 3Claude Fable 5 (xhigh)54.8%
  4. 4Claude Opus 4.748.6%
  5. 5Claude Opus 4.846.7%
  6. 6GPT-5.5 (xhigh)44.8%
  7. 7Gemini 3.8 Flash44.8%
  8. 8GPT-5.4 (xhigh)44.3%
  9. 9GLM 5.242.4%
  10. 10GPT-5.3 Chat (xhigh)42.4%
  11. 11Claude Opus 4.635.6%
  12. 12Gemini 3.1 Pro33.8%
  13. 13Claude Sonnet 4.632.2%
  14. 14GLM-524.2%
  15. 15Kimi K2.520.9%
17 of 17
#
1GPT-6 Astraxhigh59.0%66.82026-09-09
2Claude Fable 5.1xhigh56.7%65.42026-09-02
3Claude Fable 5xhigh54.8%–2026-06-11
4Claude Opus 4.748.6%63.12026-05-06
5Claude Opus 4.846.7%60.02026-06-08
6GPT-5.5xhigh44.8%64.32026-05-06
7Gemini 3.8 Flash44.8%54.42026-09-09
8GPT-5.4xhigh44.3%63.22026-05-06
9GLM 5.242.4%51.52026-06-23
10GPT-5.3 Chatxhigh42.4%–2026-05-06
11Claude Opus 4.635.6%62.32026-05-06
12Gemini 3.1 Pro33.8%60.52026-05-06
13Claude Sonnet 4.632.2%58.22026-05-06
14GLM-524.2%54.82026-05-06
15Kimi K2.520.9%54.22026-05-06
16MiniMax M2.519.5%53.62026-05-06
17Gemini 3 Flash10.0%56.92026-05-06

More coding benchmarks · All LLM benchmarks

Related benchmarks

Top head-to-heads on SWE Atlas: Refactoring

Cite as: BenchLeader, “SWE Atlas: Refactoring leaderboard”, data as of 6 Nov 2026, https://www.benchleader.com/benchmarks/scale_sweatlas_refactoring.

SWE Atlas: Refactoring: questions

What does SWE Atlas: Refactoring measure?
Multi-file refactors in real repositories, checked by tests and review criteria. Scores are reported in percent of tasks solved; higher is better.
What is the top score on SWE Atlas: Refactoring?
As of 6 Nov 2026, the highest score on SWE Atlas: Refactoring is 59.0% by GPT-6 Astra (result dated 9 Sep 2026), ahead of Claude Fable 5.1 at 56.7%. Scores come from Scale AI SEAL and are re-read daily.
Which AI model leads SWE Atlas: Refactoring?
GPT-6 Astra leads SWE Atlas: Refactoring with 59.0% as of 6 Nov 2026 (result dated 9 Sep 2026), ahead of Claude Fable 5.1 at 56.7%.
How many models have SWE Atlas: Refactoring results?
17 model configurations have a SWE Atlas: Refactoring result on BenchLeader, all taken from Scale AI SEAL.
Who runs SWE Atlas: Refactoring and how often is it updated?
SWE Atlas: Refactoring is published by Scale AI SEAL. BenchLeader re-reads the published results once a day and records the date each result was published.
Does SWE Atlas: Refactoring count toward the BenchLeader Index?
No. SWE Atlas: Refactoring is shown for reference but left out of the composite index.