Grok 4.20 0309 (Reasoning)
SpaceXAIGrokProprietary
Description
Grok 4.20 Beta Reasoning is xAI's reasoning-optimized variant of the Grok 4.20 model family. Released as a beta on March 9, 2026, it uses thinking tokens for enhanced chain-of-thought reasoning, featuring a 2 million token context window for complex problem-solving tasks.
Release Date
2026-03-10
Parameters
—
Context Length
—
Modalities
image, text
Capability Radar
27
general
0
coding
88
reasoning
71
science
30
agents
80
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Agentic Capability | 97 | 35.0 | LS |
| Code Ranking | 180 | 69.0 | AA |
| General Ranking | 69 | 70.0 | AA |
| Science | 105 | 72.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Agents
Finance Agent v2
28.5%
AA Evaluation Indices
(Artificial Analysis)Tau2(Sierra + U Toronto + Vector Institute (2025))96.5
Gpqa(NYU + Cohere + Anthropic (2023))88.5
Ifbench(Google Research (2023))82.9
Lcr(Artificial Analysis)67.7
Terminalbench Hard(Stanford × Laude Institute (2026))40.9
Hle(Center for AI Safety + Scale AI (2025))32.4
Intelligence Index(Artificial Analysis)25.2
LLM Stats Category Scores
(LLM Stats (zeroeval))Long Context30
Reasoning30
Finance30
General30
Agents30
Pricing
Input Price$2 / 1M tokens
Output Price$6 / 1M tokens
Blended Price (3:1)$3 / 1M tokens
Speed
Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s
Provider Price Ranking
Provider Price Ranking
1 providers
ProviderInputOutput
1SpaceXAIPRIMARY
$2
$6
Compare pricing across different API providers for this model.