Benchmark Heaven: AI model benchmarks with sources and modeled costs, plus the JevBench and ImageJevBench decision model leaderboards.
☆21Oct 17, 2026Updated this week
Alternatives and similar repositories for model-market-comparison
Users that are interested in model-market-comparison are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Memory system for pi.☆73Aug 24, 2026Updated last month
- Benchmark local LLM serving by replaying real agent trajectories☆99Updated this week
- ☆42Sep 21, 2026Updated 3 weeks ago
- Develop on your own machine from anywhere—Docker, databases, Vite and all.☆49Sep 26, 2026Updated 3 weeks ago
- Permissive UTF-8/16/32 transcoding, comparison and BOM detection with SIMD ASCII fast paths☆21Oct 9, 2026Updated last week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- a node-based graphic design tool☆136Aug 7, 2026Updated 2 months ago
- Benchmark for how well different models search codebases☆16Jun 9, 2026Updated 4 months ago
- Harness/code for DrivingBench v1, which allows frontier LLMs to control cars via Comma/openpilot + MCP tools.☆59Sep 26, 2026Updated 3 weeks ago
- ☆98Sep 8, 2026Updated last month
- A procedural Three.js WebGPU recreation of Monica's apartment from Friends.☆28Sep 5, 2026Updated last month
- A self-documenting, self-extending multi-agent system. Topics are miniature GOOP instances. Markdown is the API between human and machine…☆44Jul 14, 2026Updated 3 months ago
- Routes each request to the right AI agent or skill before your AI picks one. Your rules decide what code can; Jev (TypeSafe) makes the ty…☆20Sep 23, 2026Updated 3 weeks ago
- Reproduction package for "Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity" — ten agent arms across AppWorld…☆35Oct 10, 2026Updated last week
- ☆58Oct 1, 2026Updated 2 weeks ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- ☆39Oct 6, 2026Updated last week
- Process-global proxy routing for Node.js☆33Oct 1, 2026Updated 2 weeks ago
- Multi-provider AI agent CLI written in Rust☆41Oct 1, 2026Updated 2 weeks ago
- Danny's Bevy exploration☆24Apr 12, 2024Updated 2 years ago
- Open source, clear, transparent, real world llm benchmarks☆92Updated this week
- ☆52Sep 25, 2026Updated 3 weeks ago
- ☆71Aug 10, 2026Updated 2 months ago
- Skills that drive best-in-class engineering☆199Oct 5, 2026Updated last week
- Speak anywhere on macOS; the text lands where you point. Menu-bar dictation that writes into the focused field — at the end of existing t…☆62Oct 2, 2026Updated 2 weeks ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- An agent skill that plays ARC-AGI-3. One rule: say what an action will do before you spend it. Claude Code on Opus 5 finished all 25 publ…☆90Aug 19, 2026Updated last month
- AsyncTimewarp by Comrade Stinger☆12Feb 10, 2023Updated 3 years ago
- A JS wrapper for U of I's Course Schedule/Catalog API☆10Oct 6, 2022Updated 4 years ago
- Dictation extension for pi.☆72Aug 31, 2026Updated last month
- ☆24Feb 19, 2024Updated 2 years ago
- Audit, write, and set up clear, credible social profiles with evidence-backed positioning and verified, approved updates.☆24Sep 9, 2026Updated last month
- ☆74Updated this week
- lightweight autograd lib in C☆47Apr 26, 2026Updated 5 months ago
- Interactive-rebase style tree navigation and compaction for pi☆32Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Dual-engine (llama.cpp + vLLM) LLM benchmarking pipeline for GGUF & safetensors on NVIDIA GPUs — speed, quality, live dashboard, publisha…☆41Updated this week
- Manage upto 1000 agents using automations and workflows☆39Oct 11, 2026Updated last week
- The Cartographer's Desk — a hand-painted, scrollable field map of Jake Van Clief's career. One HTML file, Three.js, a traveling fox.☆125Aug 26, 2026Updated last month
- ☆88Updated this week
- An open-source MCP server that turns any LLM into an Intelligent Tutoring System. 50 years of cognitive science, MIT licensed.☆51Updated this week
- CyberGym-E2E is a large-scale benchmark built from real-world vulnerabilities in widely used open-source projects to evaluate AI agents' …☆85Oct 7, 2026Updated last week
- ☆74Sep 23, 2026Updated 3 weeks ago