# AI 框架（Harness）对模型性能的影响超过模型本身：GPT-5.5 在 Cursor 上得分 87.2%，比 Codex 高 25.7 个百分点

- 来源：Tomer Tunguz 博客（VC 分析）
- 发布时间：2026-07-28 08:00
- AIHOT 分数：58
- AIHOT 链接：https://aihot.virxact.com/items/cms4y4ak403euroa107laidpg
- 原文链接：https://www.tomtunguz.com/aftermarket-harnesses

## AI 摘要

Endor Labs 测试发现，同一模型在不同框架（Harness）上性能差异巨大：OpenAI 的 GPT-5.5 在原生 Codex 框架上功能正确率为 61.5%，在 Cursor 上达 87.2%；Anthropic 的 Opus 4.7 在 Claude Code 上为 87.2%，在 Cursor 上为 91.1%。

## 正文

AI harnesses have more impact on performance than the models.

Endor Labs ran the same models through two harnesses in the same week. OpenAI’s GPT-5.5 scored 61.5% functional correctness in its native Codex harness & 87.2% in Cursor’s, a 25.7-point swing from the runtime alone. Anthropic’s Opus 4.7 scored 87.2% in Claude Code & 91.1% in Cursor.1

Both frontier models performed better in a competitor’s harness than in the one their maker ships.

Harnesses are a fulcrum in the AI stack. They influence cost, quality, & accuracy.

Input tokens are 86-98% of LLM traffic on OpenRouter. Output costs 5x input per token, but input still dominates the bill because there is so much more of it. One year ago I wondered about this ratio in the Hungry, Hungry AI Model.2 Practitioners said 95% input/5% output. At scale, they were right.

Controlling input costs is therefore a valuable proposition. The model doesn’t control those costs, but the harness does.3 Harnesses decide which context to send. Much of that context repeats from query to query. Caching it intelligently can save 40-80%. A study across 500 long-horizon agent sessions found 41-80% cost reduction & 13-31% faster time-to-first-token, with savings scaling linearly from 500- to 50,000-token prompts.4 The winner was caching only the stable prefix & placing dynamic content after the cache breakpoint.

Harnesses also perform information retrieval: the code to read, the style guide, the section of an investment brief to analyze. The more concise & precise, the lower the cost.

Cursor’s harness matches Claude Code technique-for-technique: dynamic tool fetching, priority-based prefix assembly, two-tier caching. That is why Opus 4.7 scored higher in Cursor than in Claude Code, & why GPT-5.5 nearly doubled its functional-correctness score outside Codex.

The bundled case is not without merit. Claude Code treats cache hit rate as an uptime metric, hits about 96% in real sessions, shares the system-prompt cache across users on the same version, & builds forked sub-agents at 99% byte-identity for 90% savings.5

Co-designing the harness, cache API, & model buys real cache discipline. But the discipline lives in the harness, & a third-party harness can match it, as Cursor’s numbers show.

The harness has shed its critique as a model wrapper ; it’s a jockey pushing AI performance further than the breeder imagined.

Endor Labs, “GPT-5.5 Sets a New Code Security Record with Cursor, not Codex, in Agent Security League,” Apr 27, 2026, https://www.endorlabs.com/learn/gpt-5-5-sets-a-new-code-security-record-with-cursor-not-codex-in-agent-security-league. Agent Security League benchmark, based on Carnegie Mellon’s Open SusVibes framework. ↩︎

Tomasz Tunguz, “The Hungry, Hungry AI Model,” July 8, 2025, https://tomtunguz.com/input-output-ratio/ ↩︎

Tomasz Tunguz, “The Harness Is the New Battleground,” https://tomtunguz.com/the-harness-is-the-new-battleground/ ↩︎

Lumer et al., “Don’t Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Tasks,” arXiv:2601.06007, 2026. https://arxiv.org/abs/2601.06007 ↩︎

Anthropic, “Lessons from building Claude Code: Prompt caching is everything,” Apr 2026, https://claude.com/blog/lessons-from-building-claude-code-prompt-caching-is-everything; swap-tax figures from Digital Applied, “Prompt Caching Economics: Cache-First Agent Design,” Jul 2026, https://www.digitalapplied.com/blog/prompt-caching-economics-cache-first-agent-architecture-2026. ↩︎