#18 Grok 4.20 Beta
medium- Cost
- $0.034
- Time
- 91.0s
- Tokens
- 13,523 tok
Summary
Grok 4.20 Beta scores 8.2 on AI BENCHY and ranks #18. It has N/A reliability, a 79.6% pass rate, $0.633 total cost, and 9.81s average response time.
Archived model: this model is no longer updated or tested on new tests.
Identity note
Grok 4.20 Beta was the preview version of xAI: Grok 4.20.
8.2
Consistency
9.1
N/A
$0.633
Total Output Tokens
93,477
Total Input Tokens
0
Input Price
$0.000 / 1M
Output Price
$0.000 / 1M
Flaky tests
2
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-05-06 14:15 Re-test | 8.5 | N/A | $0.750 ↑ | Compare | |
| 2026-05-06 14:15 Re-test | 8.2 | N/A | $0.633 | Compare | |
| 2026-05-06 14:15 Re-test | 8.2 | N/A | $0.633 | Compare | |
| 2026-05-06 14:15 Suite changed | 8.2 | N/A | $0.633 | Current run | |
| 2026-04-11 01:19 First recorded run | 8.0 | N/A | $0.633 | Compare |
This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.
Run comparison
| Run | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|
| 2026-05-06 14:15 · Suite changed | 8.2 | 9.1 | N/A | 13/18 | 2 | 93,477 | 0 | $0.633 | 9.81s |
| 2026-05-06 14:15 · Re-test | 8.5 | 9.5 | N/A | 14/18 | 1 | 93,212 | 35,955 | $0.750 | 9.75s |
| Difference | -0.3 | -0.4 | -1 | +1 | +265 | -35955 | -$0.118 | +63ms |
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 8.7 | 7.9 | |
| Coding | 10.0 | 10.0 | |
| Combined | 10.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 5.3 | 10.0 | |
| General Intelligence | 10.0 | 10.0 | |
| Instructions following | 9.8 | 10.0 | |
| Puzzle Solving | 8.2 | 7.2 | |
| Tool Calling | 3.0 | 10.0 |