Grok 4.5 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.
Tested on 21 benchmarks · BenchGecko score 61.7. Top scores: Chatbot Arena Elo — Coding (1551.8%), Chatbot Arena Elo — Overall (1465.8%), OTIS Mock AIME 2024-2025 (97.8%).
gpt-oss-20b (free) scores 61.0 (99% as good) at $0.00/1M input · 100% cheaper
Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.
Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.
Deceptively simple questions that humans find easy but AI models often get wrong. Tests common sense and reasoning gaps.
ARC-AGI 2, harder sequel to ARC. More complex abstract reasoning patterns that test generalization ability beyond training data.
Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.
- Typemultimodal
- Context500K tokens (~250 books)
- ReleasedJul 2026
- LicenseProprietary
- StatusActive
- Cost / Message~$0.010
Frequently Asked Questions
Related Models
PaLM 2-S · Unknownphi-3-mini 3.8B · MicrosoftQwen3.6 27B · Alibaba QwenWizardLM-2 8x22B · MicrosoftGPT-5.6 Luna · OpenAIKey facts · as of 2026-10-21
- Grok 4.5 by xAI. BenchGecko score 61.7, rank 78 of 320 scored models (normalized average of public benchmark scores).
- List price $2.00 input · $6.00 output per 1M tokens (as of 2026-10-21).
- Sold by 4 providers (as of 2026-10-21): xAI $2.00 in / $6.00 out · xAI $2.00 in / $6.00 out · xAI $4.00 in / $12.00 out · xAI $4.00 in / $12.00 out. Every provider
- Gecko Tests · Gecko Score 46 (rank 28): Who Are You B (Knows who made it) · Knowledge Horizon E (Knows news up to Feb 2025) · Tokenizer Tax C (50% more tokens outside English).
How to cite · data as of 2026-10-21
Grok 4.5 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-21. https://benchgecko.ai/model/grok-4-5
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP