Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...
Tested on 15 benchmarks · BenchGecko score 56.5. Top scores: OTIS Mock AIME 2024-2025 (92.2%), ARC-AGI (89.5%), GPQA diamond (85.8%).
Qwen2.5 Coder 7B Instruct scores 56.3 (100% as good) at $0.03/1M input · 98% cheaper
Complex terminal-based engineering tasks. Models must use command-line tools, navigate filesystems, and debug systems through shell interaction.
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.
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
- Context2.0M tokens (~1,000 books)
- ReleasedMar 2026
- LicenseProprietary
- StatusActive
- Cost / Message~$0.005
Frequently Asked Questions
Key facts · as of 2026-10-05
- Grok 4.20 by xAI. BenchGecko score 56.5, rank 108 of 312 scored models (normalized average of public benchmark scores).
- List price $1.25 input · $2.50 output per 1M tokens (as of 2026-10-05).
- Sold by 4 providers (as of 2026-10-05): xAI $1.25 in / $2.50 out · xAI $1.25 in / $2.50 out · xAI $2.50 in / $5.00 out · xAI $2.50 in / $5.00 out. Every provider
- Gecko Tests: Who Are You B (Knows who made it) · Tokenizer Tax B (44% more tokens outside English).
How to cite · data as of 2026-10-05
Grok 4.20 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/grok-4-20
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