EvalScope is a framework for evaluating and stress-testing large language, vision-language, embedding, reranking, and generative models, with tools for running benchmarks and reviewing results. It is for developers and researchers comparing model capabilities, agent behavior, and inference performance. The catalogue add-ons provide workflows for running evaluations and interpreting their outputs.
Borrowing it
Nothing to install: this file belongs to modelscope/evalscope. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/modelscope/evalscope/main/AGENTS.mdgit clone --depth 1 https://github.com/modelscope/evalscopeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/modelscope/evalscope/agents-md)<a href="https://agentmods.dev/instructions/modelscope/evalscope/agents-md"><img src="https://agentmods.dev/badge/instructions/modelscope/evalscope/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/modelscope/evalscope/agents-md"><img src="https://agentmods.dev/badge/instructions/modelscope/evalscope/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.03229 | $0.03229 |
| Opus 5.5 | $0.01292 | $0.01292 |
| Sonnet 5.5 | $0.00646 | $0.00646 |
| Haiku 4.5 | $0.00323 | $0.00323 |
Grade A, and why
evalscope AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
EvalScope — LLM evaluation framework with a registry-based plugin architecture. This file is the contract for AI coding agents working in this repo.
Setup
pip install -e . # basic install
make dev # dev + perf + docs extras + pre-commit
Python ≥ 3.10 (3.10 / 3.11 / 3.12). Dependencies: requirements/framework.txt + pyproject.toml [project.optional-dependencies] (extras: opencompass, vlmeval, rag, perf, app, aigc, sandbox, service, dev, docs, all, plus per-benchmark extras).
Build, lint, test
make lint # apply Ruff fixes/formatting and run all pre-commit checks
make lint-imports # architecture contracts (import direction, see .importlinter)
pytest tests/cli/test_all.py::TestRun::test_ci_lite -v -s -p no:warnings # CI smoke test
pytest tests/perf/test_perf_basic.py::TestPerfBasic::test_multi_parallel_sweep -v -s # perf
Commits failing make lint are rejected on main.
Choose validation for the changed behavior: targeted tests for code changes, perf tests for perf changes, and diff/link/format checks for documentation-only or instruction-only edits. Run the Submission checks before committing. After relevant checks pass, repeat or broaden them only for new changes, failures, or unresolved concerns. Local checks and fixes within the requested scope do not need repeated approval.
Docs generation
Benchmark detail pages (docs/{zh,en}/benchmarks/<name>.md) and meta cache (evalscope/benchmarks/_meta/<name>.json) are auto-generated from each adapter's BenchmarkMeta.description + dataset statistics. Do not hand-edit those files.
Every BenchmarkMeta.description must be English Markdown with these sections in this order:
## Overview: benchmark purpose and scope.## Task Description: bullet fields forTask Type,Input,Output, andDomain(use a more precise fourth field such asModalitiesorGradingonly whenDomaindoes not apply).## Key Features: dataset scale/source, evaluated capabilities, and version-specific behavior.## Evaluation Notes: metrics, scoring procedure, runtime/dependency requirements, and compatibility limits.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +2 lines · +268 tokens per session d9b002628ae6
- 1mo ago Changed · +5 lines · +81 tokens per session d609eff2f037
- 1mo ago Changed · -15 tokens per session af88609e66ea
- 2mo ago First seen · 173 lines · 2,895 tokens per session scan A f46c3186f0ff
evalscope AGENTS.md is an instructions file published in the GitHub repository modelscope/evalscope (3,607 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,229 tokens to every session, about $0.0129 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.