cd /news/artificial-intelligence/cursorbench-grok-4-5-better-than-gpt… · home topics artificial-intelligence article
[ARTICLE · art-51556] src=cursor.com ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

Cursorbench: Grok 4.5 better than GPT-5.5, at ~half the cost

Grok 4.5 outperforms GPT-5.5 on CursorBench at roughly half the cost, though an earlier snapshot of the Cursor codebase was accidentally included in Grok 4.5's training, potentially inflating its score. The data has been removed for future models.

read1 min views6 publishedJul 8, 2026
Cursorbench: Grok 4.5 better than GPT-5.5, at ~half the cost
Image: Cursor (auto-discovered)
  • Grok 4.5 has an advantage on CursorBench: an earlier snapshot of the Cursor codebase was accidentally included in training. The exact score impact is unclear. That data has been removed for future models, and was not present for Composer models in the past. Changelog

CursorBench 3.2

Introduced instruction following and advanced tool use problems.

CursorBench 3.1

Introduced problems focused on codebase understanding, bugfinding, planning, and code review.

Improved grading criteria for some edit tasks.

CursorBench 3.0

Initial set of tasks focused on edit, refactor, and bugfix problems.

Avg cost / task is computed by applying each model's published per-million-token pricing (input, cache read, cache write, and output) to the tokens it used on each task across the CursorBench 3.2 benchmarks, then averaging with the same task weights as the CursorBench 3.2 score. Results are subject to variance; small differences in scores may not be statistically meaningful.

  • Grok 4.5 has an advantage on CursorBench: an earlier snapshot of the Cursor codebase was accidentally included in training. The exact score impact is unclear. That data has been removed for future models, and was not present for Composer models in the past. Changelog

CursorBench 3.2

Introduced instruction following and advanced tool use problems.

CursorBench 3.1

Introduced problems focused on codebase understanding, bugfinding, planning, and code review.

Improved grading criteria for some edit tasks.

CursorBench 3.0

Initial set of tasks focused on edit, refactor, and bugfix problems.

Avg cost / task is computed by applying each model's published per-million-token pricing (input, cache read, cache write, and output) to the tokens it used on each task across the CursorBench 3.2 benchmarks, then averaging with the same task weights as the CursorBench 3.2 score. Results are subject to variance; small differences in scores may not be statistically meaningful.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @grok 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/cursorbench-grok-4-5…] indexed:0 read:1min 2026-07-08 ·