Grok 4.5
A version-specific coding and agentic knowledge-work model released through the SpaceXAI API, Grok Build, and Cursor, with developer-reported gains across engineering benchmarks and long-running tool workflows.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why this model scores 81.7
Primary launch evidence supports high coding, engineering, reasoning, office-tool, and agentic capability, including training on multi-hour rollouts. API access, low published pricing, Cursor distribution, and Grok Build make deployment broad. Strong cyber-adjacent coding and tool use create substantial misuse potential, while hosted access and the absence of an open-weight release keep deployment and residual control difficulty below freely downloadable frontier profiles.
Videos about Grok 4.5
Reviewed videos from Artificial Intelligence Videos. These links add context and never change a DoomBench score.
News tied to Grok 4.5
The model score of 81.7 rates this model's risk profile. The overall Doom Index of 66.8 measures the complete temporally weighted evidence record. These values answer different questions.
Each article's current Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores use a bounded temporal offset around their technical profile, but never feed back into the overall index.
SpaceXAI releases Grok 4.5 for coding and agentic knowledge work
SpaceXAI released Grok 4.5 through its API, Grok Build, and Cursor, reporting stronger coding, engineering, and long-running agentic performance. The launch also priced broad developer access and positioned the exact version as the company's most capable model.
- Full item contribution
- +0.13
- Grok 4.5 equal share
- +0.13
Model score history
-
R4
Doom Score 81.7
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-142416 under temporal-monthly-pressure-v4.
12 Aug 2026 -
R3
Doom Score 81.6
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.
12 Aug 2026 -
R2
Doom Score 81.7
Full-corpus evidence recalculated after run intensive-backfill-20260811-191225 under bounded-corpus-v2.
11 Aug 2026 -
R1
Doom Score 81.6
Initial model assessment from the dated primary Grok 4.5 launch source, filling one post-2020 historical gap.
11 Aug 2026