DeepSWE v1.1
An AI capability benchmark for software engineering tasks, evaluating a model's code comprehension, refactoring, and defect-fixing performance in real production repositories.
Timeline (last 90 days)
Gemini 4 Argon achieved a SOTA score of 77.9% on the DeepSWE v1.1 benchmark.
Argon leads on DeepSWE v1.1 with 77.9% versus Opus 5.5's 74.2%; on Terminal-Bench 4.0, Opus 5.5 leads with 66.4% versus 57.4%.
On the DeepSWE v1.1 (coding) benchmark, Gemini 4 Argon scores 77.9%, Claude Opus 5.5 scores 74.2%, and GPT-6 Astra scores 74.1%.
GLM-5.3-Flash 在 DeepSWE v1.1 得63.4分，比 GLM-5.2 的46.2分提升17.2分；HLE 得55.3分。
In the Deep Study software engineering test, Argon scored 77.9%, higher than GPT-6 Astra and Claude Opus 5.5 (both approximately 74%).
Argon set a new record of 77.9% on DeepSWE v1.1, which measures real long-horizon software engineering tasks.
On the DeepSWE v1.1 benchmark, 3.8 Flash surpasses most frontier models with larger parameter counts.
All Facts (7)
Gemini 4 Argon achieved a SOTA score of 77.9% on the DeepSWE v1.1 benchmark.
50%UnverifiedArgon leads on DeepSWE v1.1 with 77.9% versus Opus 5.5's 74.2%; on Terminal-Bench 4.0, Opus 5.5 leads with 66.4% versus 57.4%.
50%UnverifiedOn the DeepSWE v1.1 (coding) benchmark, Gemini 4 Argon scores 77.9%, Claude Opus 5.5 scores 74.2%, and GPT-6 Astra scores 74.1%.
50%UnverifiedGLM-5.3-Flash 在 DeepSWE v1.1 得63.4分，比 GLM-5.2 的46.2分提升17.2分；HLE 得55.3分。
50%UnverifiedIn the Deep Study software engineering test, Argon scored 77.9%, higher than GPT-6 Astra and Claude Opus 5.5 (both approximately 74%).
50%UnverifiedArgon set a new record of 77.9% on DeepSWE v1.1, which measures real long-horizon software engineering tasks.
50%UnverifiedOn the DeepSWE v1.1 benchmark, 3.8 Flash surpasses most frontier models with larger parameter counts.
50%