GLM-5: From Vibe Coding to Agentic Engineering
GLM-5 is a 744B-parameter MoE model (40B active) from Zhipu AI, scaled up from GLM-4.5's 355B with 28.5T pre-training tokens and DeepSeek Sparse Atten...
AI Benchmark Leaderboard
Summary
Terminal-Bench ranks AI agents in terminal tasks. Warp leads with 52% accuracy using Claude models. The list compares various frameworks and model providers.
Highlights
- Warp using claude-4-sonnet leads with 52.0% accuracy.
- Anthropic models dominate the top rankings.
- OpenAI models generally rank lower in this benchmark.
- Diverse agents like Goose and Terminus are evaluated.
- Metrics include accuracy and standard deviation.
auto-generated
Context
Audience
AI Researchers and Software Developers
DomainArtificial Intelligence
Formatinteractive leaderboard
Accessfree online
Topics
Related
Terminal AgentsClaude ModelsOpenAI ModelsAI BenchmarkingWarp Terminal