B

benchmark

Measure any tennis API against a published, reproducible method — response time, observed availability — and be told when your sample is too small to support a number.

Open dataset: bitHuman avatar render speed (× real time) by device, from docs.bithuman.ai/performance. Code Apache-2.0, data CC BY 4.0.

GitLab CI/CD components for LLM apps: fail the pipeline on likely hallucinations, prompts over their token budget, padded prompts, an LLM bill heading over budget, or slow and flaky models. Tested on every push.

Command-line benchmark for LLM APIs: send the same prompts to OpenAI and Anthropic models concurrently and compare p50/p99 latency, tokens per second, cost per request and success rate. Rust.

Объектив · Исследование распознавания техники: эталон, прогоны пайплайнов, метрики, лидерборд, выводы

Zambo: the cross-AI execution layer. 136 native MCP tools over one endpoint, with a verifiable execution receipt for every call (AER-1 open draft). Free: generous free tier, no account. Day Pass $0.99 USDC on Base for 24h; Zambo Pass $29/month ($19/month for verified $ZAMBO holders). https://zambo.dev

Header-only C++17 least-squares solver by Householder QR

Droid Tune-Up — an unofficial open-source evaluation harness for Factory Droid. Drives droid exec headless, hides tests and the solution from the agent, and grades only the committed worktree with deterministic behavioral tests. Not affiliated with Factory.

The QR benchmark set: QR codes under damage, hand-shake and rotation, each with its expected text; a viewer that runs any scanner through it on a monitor and a scorer. Verdetto's own, CC0.

Every symbology Zint encodes, rendered clean and put through graded damage: 100 formats, 10,840 images, each with the exact text its symbol carries. A ceiling test for a barcode reader. Images CC0, scripts MIT.

Helm Charts for various benchmarks

Kevlar Benchmark: OWASP Top 10 for Agentic Apps (AI-Agents) 2026 a Red Team Benchmark.

Public evidence datasets, claim atlases, and reproducible benchmarks for ClaimBound.

A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. Delirium is not an exploitation tool. It is a standardized benchmark designed to detect the precise moment when a language model's attention weights shift from serving a system prompt to serving an emergent interpersonal pattern — before harm occurs.

Red Team AI Benchmark: Evaluating LLMs for authorized offensive-security tasks. Red Team AI Benchmark is a CLI model-evaluation benchmark. It measures how LLMs understand and respond to red-team questions and security scenarios; it is not a tool for carrying out those activities. Version 2 uses a rubric-based dataset instead of judging answers only against one golden response.

Mini benchmarking suite — performance testing utilities.

Automated LLM Benchmarking on GPU - tokens/sec, latency percentiles, VRAM profiling, multi-format support (HuggingFace, GGUF, GPTQ)

https://ayinedjimi-consultants.fr

Model Verification Layer is a modular system for evaluating, comparing, and validating the behavior of large language models using structured benchmarks, logic consistency checks, cross-model consensus analysis, and policy-aware constraints. It provides a transparent framework for understanding how different AI models perform under identical conditions, enabling more reliable model selection, safer deployment, and user-adaptive decision making. https://roxanneardary.com/model-verification-layer/

Agent-shape testing harness that measures how an LLM-driven agent uses a tool's CLI, scored by an LLM judge.

Scaling and complexity benchmarks for Univec.