DeepSWE
Benchmark ● Covered in 13 stories + Follow
DeepSWE is tracked in TLDRocket’s benchmark dataset. Explore the recorded developments, relationships and supporting evidence below. Coverage reflects our monitored sources and may be incomplete.
Updated 27 October 2026
Latest developments
Q4 2026
Model release: Anthropic & Claude Fable 5.1 Model release
Q3 2026
Model release: Fugu Max & Fugu Ultra v2 Model release
Model release: Meta & Meta Superintelligence Labs Model release
Benchmark result: Claude Fable 5 & GLM-5.3 Benchmark result
Benchmark result: Claude Fable 5 & DeepSeek V4 Pro 0813 Benchmark result
Model release: Gemini 3.7 Flash & Google Model release
Model release: Meta & Muse Code Model release
Model release: DeepSeek & DeepSeek V4-Flash Model release
- Market development: Contrastive-LM & CLM-8B
- Model release: Sakana AI & Fugu Max
- Model release: Meta & Muse Spark 1.3
- Market development: GLM-5.3 Flash & GLM-5.3
- Benchmark result: GLM-5.3 & Claude Fable 5
- Benchmark result: GLM-5.3 & GPT-5.6 Sol
- Benchmark result: DeepSeek V4 Pro 0813 & GPT-5.6 Sol
- Benchmark result: DeepSeek V4 Pro 0813 & Claude Fable 5
- Model release: Google & Gemini 3.7 Flash
- Model release: DeepSeek-V4 Flash 0731 & GPT-5.6 Luna
- Model release: Meta & MetaCode
- Model release: DeepSeek & DeepSeek V4-Flash-0731
Relationships
Products & technology
- Fugu Ultra v2 derived from this benchmark · 1 source
- GLM-5.3 develops this benchmark · 1 source
- Claude Fable 5 develops this benchmark · 1 source
Competition
- Muse Wonder Full competes with this benchmark · 1 source