SWE Atlas v1.1: Codebase QnA leaderboard
As of 16 Nov 2026, the top score on SWE Atlas v1.1: Codebase QnA is 83.9% by Claude Fable 5.2 (Anthropic), ahead of Qwen3.8 Max at 81.5%, across 28 model configurations with a published result (Scale AI SEAL, result dated 11 Nov 2026). Answering questions about a large codebase, SWE Atlas v1.1. Scale AI. SWE Atlas v1.1: Codebase QnA is shown for reference only and does not count toward the BenchLeader Index.
Key facts (as of 16 Nov 2026)
- Claude Fable 5.2 holds the top SWE Atlas v1.1: Codebase QnA score at 83.9% (Scale AI SEAL, 11 Nov 2026).
- Qwen3.8 Max is second on SWE Atlas v1.1: Codebase QnA at 81.5% (Scale AI SEAL, 11 Nov 2026).
- SWE Atlas v1.1: Codebase QnA: Answering questions about a large codebase, SWE Atlas v1.1. Scale AI (Scale AI SEAL).
- 28 model configurations have a published SWE Atlas v1.1: Codebase QnA result on BenchLeader (BenchLeader, 16 Nov 2026).
- SWE Atlas v1.1: Codebase QnA does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).
Answering questions about a large codebase, SWE Atlas v1.1. Scale AI.
- Published by
- Scale AI SEAL
- Category
- Coding
- Index weight
- Reference only
- Models
- 28
- Data as of
- 16 Nov 2026
- Newest result
- 11 Nov 2026
Scale AI SEAL Leaderboards.
Not comparable with the earlier test of the same name, whose final scores stay on SWE Atlas v1.0: Codebase QnA.
- 1Claude Fable 5.283.9%
- 2Qwen3.8 Max (max)81.5%
- 3Claude Fable 5.179.0%
- 4Claude Opus 5.577.4%
- 5Inkling 2 Small74.2%
- 6Claude Sonnet 5.574.2%
- 7Muse Wonder73.4%
- 8Gemini 4 Carbon73.4%
- 9Grok 4.773.4%
- 10GPT-6.1 Sol71.0%
- 11DeepSeek V4.1 Flash71.0%
- 12GPT-6 Astra70.2%
- 13Kimi K3.1 Pro70.2%
- 14GLM 5.370.2%
- 15GLM 5.3 Flash66.9%
| # | ||||
|---|---|---|---|---|
| 1 | New | 83.9% | 65.4 | 2026-11-11 |
| 2 | 81.5% | 58.7 | 2026-11-11 | |
| 3 | 79.0% | 66.4 | 2026-11-06 | |
| 4 | 77.4% | 61.0 | 2026-11-06 | |
| 5 | 74.2% | 57.9 | 2026-11-06 | |
| 6 | 74.2% | – | 2026-11-06 | |
| 7 | 73.4% | 64.4 | 2026-11-06 | |
| 8 | 73.4% | – | 2026-11-11 | |
| 9 | 73.4% | – | 2026-11-06 | |
| 10 | 71.0% | 62.0 | 2026-11-06 | |
| 11 | 71.0% | – | 2026-11-06 | |
| 12 | 70.2% | 66.4 | 2026-11-06 | |
| 13 | 70.2% | 61.8 | 2026-11-11 | |
| 14 | 70.2% | – | 2026-11-11 | |
| 15 | 66.9% | 57.8 | 2026-11-11 | |
| 16 | 65.3% | 64.4 | 2026-11-06 | |
| 17 | 65.3% | 60.7 | 2026-11-06 | |
| 18 | 62.1% | – | 2026-11-06 | |
| 19 | 61.3% | 52.9 | 2026-11-11 | |
| 20 | New | 61.3% | – | 2026-11-11 |
| 21 | 54.0% | – | 2026-11-06 | |
| 22 | 50.8% | – | 2026-11-06 | |
| 23 | 50.0% | – | 2026-11-06 | |
| 24 | 49.2% | 56.1 | 2026-11-11 | |
| 25 | 45.2% | 56.4 | 2026-11-06 | |
| 26 | 26.6% | 45.8 | 2026-11-11 | |
| 27 | 21.8% | 42.1 | 2026-11-11 | |
| 28 | 10.5% | 46.1 | 2026-11-11 |
AI coding benchmark leaderboard · All LLM benchmarks
Related benchmarks
Top head-to-heads on SWE Atlas v1.1: Codebase QnA
Cite as: BenchLeader, “SWE Atlas v1.1: Codebase QnA leaderboard”, data as of 16 Nov 2026, https://www.benchleader.com/benchmarks/scale_swe_atlas_qna.
SWE Atlas v1.1: Codebase QnA: questions
- What does SWE Atlas v1.1: Codebase QnA measure?
- Answering questions about a large codebase, SWE Atlas v1.1. Scale AI. Scores are reported in percent of tasks solved; higher is better.
- What is the top score on SWE Atlas v1.1: Codebase QnA?
- As of 16 Nov 2026, the highest score on SWE Atlas v1.1: Codebase QnA is 83.9% by Claude Fable 5.2 (result dated 11 Nov 2026), ahead of Qwen3.8 Max at 81.5%. Scores come from Scale AI SEAL and are re-read daily.
- Which AI model leads SWE Atlas v1.1: Codebase QnA?
- Claude Fable 5.2 leads SWE Atlas v1.1: Codebase QnA with 83.9% as of 16 Nov 2026 (result dated 11 Nov 2026), ahead of Qwen3.8 Max at 81.5%.
- How many models have SWE Atlas v1.1: Codebase QnA results?
- 28 model configurations have a SWE Atlas v1.1: Codebase QnA result on BenchLeader, all taken from Scale AI SEAL.
- Who runs SWE Atlas v1.1: Codebase QnA and how often is it updated?
- SWE Atlas v1.1: Codebase QnA 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 v1.1: Codebase QnA count toward the BenchLeader Index?
- No. SWE Atlas v1.1: Codebase QnA is shown for reference but left out of the composite index.