Terminal-Bench 4.0
Benchmark ● Covered in 11 stories + Follow
Terminal-Bench 4.0 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.
Latest developments
2026
Open source release: Mistral & Mistral AI Open source release
Model release: Claude Opus 5.5 & Gemini 4 Argon Model release
Model release: Kim K3.1 Pro & Kimi 3.1 Pro 104B-2.8T Model release
Open source release: DeepInfer & DeepSeek Open source release
Model release: Amazon Bedrock & Anthropic Model release
Model release: AWS & Anthropic Model release
Model release: Grok 4.6 & Grok 4.7 Model release
- Open source release: Mistral & Hugging Face
- Model release: Google & Gemini 4 Carbon
- Model release: Moonshot AI & Kimi K3.1 Pro
- Open source release: DeepSeek & DeepSeek-V4.1-Flash-1017
- Market development: Anthropic & Claude Haiku 5.5
- Model release: Anthropic & Claude Sonnet 5.5
- Model release: Anthropic & AWS
- Model release: Anthropic & Claude Sonnet 5.5
- Market development: Deep Learning Weekly & Anthropic
- Model release: SpaceXAI & Grok 4.7
- Market development: Weave Engineering Intelligence & Weave Router 2.0
Relationships
Products & technology
- Claude Sonnet 5.5 develops this benchmark · 1 source
- DeepSeek-V4.1-Flash-1017 derived from this benchmark · 1 source
- Kimi K3.1 Pro integrated with this benchmark · 1 source
- Gemini 4 Carbon derived from this benchmark · 1 source
- Mistral Large 4 deploys this benchmark · 1 source
- ML4 (Le Chonk) deploys this benchmark · 1 source