Nerf Watch

dev.tokenusage/nerfwatch

Daily Nerf Watch scores for Claude and GPT models on one private, code-graded suite. Read-only.

Yes, your AI can use this right now.Answered a live MCP handshake in 204 ms with no sign-in needed and exposes 2 tools.
Is this your server? Claim the listing. Verified adds a vendor-confirmed mark on this page and matching app pages.
Claim with Verified — $49/moWant it in front of people comparing Developer Tools tools? Feature it — $149/mo

Connect it

Settings → Connectors → Add custom connector
URL: https://tokenusage.dev/mcp/nerfwatch

2 tools, pulled live

Pulled straight from the server with tools/list on 2026-10-27.
get_nerfwatch_scoresread-only

Latest public Nerf Watch scores, previous runs, changes and baselines for at most 100 models, ordered by provider, name and model id. No arguments. Histories are available through get_nerfwatch_history. Scores and changes are rounded to two decimals; comparisons are within one suite version. A lower score is a lower score on this suite, not proof that a provider changed a model. Unofficial, not af

get_nerfwatch_historyread-only

Retained public Nerf Watch score history for one model, oldest first, including each point's suite version. The required model id is available from get_nerfwatch_scores. Missing days are missing, not zero; comparisons are within one suite version. A lower score is a lower score on this suite, not proof that a provider changed a model. Unofficial, not affiliated with OpenAI or Anthropic. Source: ht

Alternatives in Developer Tools

Compare →
Try “Notion”, “Stripe”, “create invoice”, “browser”