#89 xAI: Grok 4.20
none- Cost
- $0.004
- Time
- 6.5s
- Tokens
- 1,367 tok
X AI
Release: 2026-03-31
Tested on: 2026-04-11 01:44
x-ai/grok-4.20::none
~1T total (~100B active)MoEClosedEstimated
(medium)
(none)
Summary
Grok 4.20 scores 5.2 on AI BENCHY and ranks #89. It has N/A reliability, a 29.6% pass rate, $0.095 total cost, and 1.11s average response time.
What makes Grok 4.20 unique: Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.
Identity note
Grok 4.20 Beta was the preview version of Grok 4.20.
Model facts
Researched on 2026-08-12
- Parameters
- ~1T total (~100B active)
- Architecture
- MoE
- Availability
- Closed
- License
- -
Best estimate from public evidence; the vendor did not disclose every value. xAI does not disclose the architecture or count.
5.2
Consistency
9.5
N/A
$0.095
Total Output Tokens
1,967
Total Input Tokens
0
Input Price
$2.000 / 1M
Output Price
$6.000 / 1M
Flaky tests
1
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
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 14:16 Re-test | 4.1 | N/A | $0.057 ↓ | Compare | |
| 2026-05-06 14:16 Re-test | 4.1 | N/A | $0.057 ↓ | Compare | |
| 2026-05-06 14:16 Re-test | 5.4 | N/A | $0.057 ↓ | Compare | |
| 2026-05-06 14:16 Re-test | 5.4 | N/A | $0.095 | Compare | |
| 2026-05-06 14:16 Re-test | 5.4 | N/A | $0.095 | Compare | |
| 2026-05-06 14:16 Suite changed | 5.4 | N/A | $0.095 | Compare | |
| 2026-04-11 01:44 First recorded run | 5.2 | N/A | $0.095 | Current run |
Run comparison
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-04-11 01:44 · First recorded run | 54/54 attempts | 5.2 | 9.5 | N/A | 5/18 | 1 | 1,967 | 0 | $0.095 | 1.11s |
| 2026-05-06 14:16 · Re-test | 54/54 attempts | 4.1 | 8.1 | N/A | 6/18 | 0 | 1,923 | 41,313 | $0.057 | 1.11s |
| Difference | — | +1.1 | +1.4 | -1 | +1 | +44 | -41313 | +$0.038 | +4ms |
These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.
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
Grok 4.20nonevsGLM 4.7 FlashmediumGrok 4.20nonevsLing 3.0 TinynoneGrok 4.20nonevsLaguna S 2.1noneFree AvailableGrok 4.20nonevsGranite 4.1 8BnoneGrok 4.20nonevsMiniMax M2.5mediumGrok 4.20nonevsNemotron 3.5 LightningnoneFree AvailableGrok 4.20nonevsQwen3 Coder NextmediumGrok 4.20nonevsLing 3.0 TinyhighGrok 4.20nonevsMercury 2noneGrok 4.20nonevsLing 3.0 Tinylow
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 4.8 | 10.0 | |
| Coding | 3.4 | 9.3 | |
| Combined | 3.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 3.0 | 10.0 | |
| General Intelligence | 4.8 | 10.0 | |
| Instructions following | 4.8 | 10.0 | |
| Puzzle Solving | 5.3 | 7.4 | |
| Tool Calling | 10.0 | 10.0 |