Grok 4.20 0309 (Non-reasoning)
xAIGrokProprietary
Description
Grok 4.20 Beta Non-Reasoning is xAI's non-reasoning variant of the Grok 4.20 model family. Released as a beta on March 9, 2026, it provides fast, direct responses without thinking tokens, featuring a 2 million token context window while optimizing for speed and lower latency.
Release Date
2026-03-10
Parameters
—
Context Length
2.0M
Modalities
file, image, text
Capability Radar
28
general
26
coding
79
reasoning
51
scienceest.
0
agents
80
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 231 | 37.0 | AA |
| General Ranking | 179 | 53.0 | AA |
| Science | 99 | 62.0 | AA |
Benchmark Scores (LLM Stats)
No benchmark data available
AA Evaluation Indices
Intelligence Index29.7
Coding Index25.4
Gpqa0.8
Tau20.7
Ifbench0.5
Scicode0.3
Hle0.2
Terminalbench Hard0.2
Lcr0.2
LLM Stats Category Scores
Long Context20
Pricing
Input Price$2 / 1M tokens
Output Price$6 / 1M tokens
Blended Price (3:1)$3 / 1M tokens
Speed
Tokens/sec96.4 tokens/s
Time to First Token0.47s
Time to Answer0.47s
Available Providers
(LS internal units)| Provider | Input Price | Output Price |
|---|---|---|
| xAI | 2.0M | 6.0M |