# Grok 4.20 Beta

Grok 4.20 Beta is an AI model released by SpaceXAI on Feb 17 2026. At release it scored 56% on BullshitBench v2, 76.7% on SWE-Bench Verified and 53.3% on ARC-AGI-2.

## Facts

| Field | Value |
| --- | --- |
| Model | Grok 4.20 Beta |
| Developer | SpaceXAI |
| Release date | Tuesday, Feb 17 2026 |
| Licensing | Proprietary |

## API pricing

All rates in USD per 1,000,000 tokens, pay-as-you-go.

| Tier | Input | Cached input | Output |
| --- | --- | --- | --- |
| Under 200K input tokens | $1.25 | $0.20 | $2.50 |
| At least 200K input tokens | $2.50 | $0.40 | $5.00 |

Verified August 18, 2026 against the first-party source: https://docs.x.ai/developers/pricing

## Benchmark scores published at release

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| BullshitBench v2 | 56% | [BullshitBench](https://github.com/petergpt/bullshit-benchmark) | Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. |
| SWE-Bench Verified | 76.7% | [BenchLM](https://benchlm.ai), retrieved 2026-08-31 | Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. |
| ARC-AGI-2 | 53.3% | [BenchLM](https://benchlm.ai), retrieved 2026-07-11 | Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. |

## Questions and answers

### When was Grok 4.20 Beta released?

Grok 4.20 Beta was released by SpaceXAI on Tuesday, Feb 17 2026.

### Who made Grok 4.20 Beta?

Grok 4.20 Beta was built by SpaceXAI. Elon Musk's AI company building the Grok series of models. Founded in 2023 as xAI, now part of SpaceX. Cursor (Anysphere) and its Composer coding models were acquired in 2026 and are tracked here.

### How much does Grok 4.20 Beta cost?

Grok 4.20 Beta costs $1.25 per million input tokens and $2.50 per million output tokens through the SpaceXAI API. Cached input is $0.20 per million tokens. Those are the rates for the “Under 200K input tokens” tier; 1 other pricing tier is published for this model. Rates are pay-as-you-go API prices verified against SpaceXAI's published pricing on August 18, 2026.

### What benchmark scores did Grok 4.20 Beta get?

Grok 4.20 Beta reports 3 tracked benchmark scores — BullshitBench v2: 56%; SWE-Bench Verified: 76.7%; ARC-AGI-2: 53.3%. Scores are the figures published at release by SpaceXAI.

### Is Grok 4.20 Beta open source?

No. Grok 4.20 Beta is a proprietary model. The weights are not published — it is available only through the provider's own API, apps, or partner platforms.

### What came before and after Grok 4.20 Beta?

SpaceXAI's previous tracked release was Composer 1.5 on Feb 9 2026, 8 days earlier. It was followed by Composer 2 on Mar 19 2026.


---

Canonical page: https://aireleasetracker.com/model/xai/grok-4.20-beta
Full dataset: https://aireleasetracker.com/llms-full.txt · JSON: https://aireleasetracker.com/models.json
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.