What it measures
- DeepSWE v1.1
DeepSWE v1.1
DeepSWE v1.1 result records from the supplied 2026 frontier model reports.
How to read the score
% score; higher is better.
Sourced Ranking
| Rank | Model | Provider | Score | Source | Source Type | Verified |
|---|---|---|---|---|---|---|
| 1 | Gemini 4 Argon | 77.9 | Gemini 4 Argon: our next era of frontier intelligence Accessed 2026-10-02 | official | Yes | |
| 2 | GPT-6.1 Sol | OpenAI | 75.2 | GPT-6.1 Sol cost-performance chart transcription Accessed 2026-10-02 | community | Yes |
| 3 | GPT-6 Astra | OpenAI | 74.1 | GPT-6 Astra: A new generation of intelligence Accessed 2026-09-04 | official | Yes |
| 4 | Gemini 3.8 Flash | 73.7 | Gemini 3.8 Flash model card Accessed 2026-09-04 | official | Yes | |
| 5 | Gemini 3.7 Flash | 65.3 | Gemini 3.7 Flash model card Accessed 2026-09-02 | official | Yes | |
| 6 | GLM-5.3-Flash | Z.ai | 63.4 | GLM-5.3-Flash official release and benchmark report Accessed 2026-09-04 | official | Yes |
| 7 | Qwen3.8-Flash | Alibaba Cloud | 58.7 | Qwen3.8-Flash-Next model card Accessed 2026-09-04 | official | Yes |
Limitations
- Scores may not be directly comparable across model reports, harnesses, or task releases.
- Preserve the exact version, evaluation configuration, and reporting source in each result row.
- Vendor and third-party scores are stored as raw evidence and are not automatically used in the five-axis capability radar.
leaderboard
DeepSWE v1.1 source record
Preserve the exact version, evaluation configuration, and reporting source in each result row. Vendor and third-party scores are stored as raw evidence and are not automatically used in the five-axis capability radar.