Advertise here
#80

Grok 4.20 Multi Agent Beta

X AI Release: 2026-03-12 Tested on: 2026-05-06 14:16 x-ai/grok-4.20-multi-agent-beta::medium
~1T total (~100B active)MoEClosedEstimated

Summary

Grok 4.20 Multi Agent Beta scores 6.6 on AI BENCHY and ranks #80. It has N/A reliability, a 63.0% pass rate, $5.074 total cost, and 9.80s average response time.

Archived model: this model is no longer updated or tested on new tests.

Model facts

Researched on 2026-08-12

Estimated
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.

Parameter source Availability source

Score

6.6

Consistency

7.4

Reliability

N/A

Total Cost (Current Price)

$5.074

Total Output Tokens

608,704

Total Input Tokens

0

Input Price

$0.000 / 1M

Output Price

$0.000 / 1M

Cache Read Price

N/A

Cache Write Price

N/A

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 10

Attempt pass rate: 63.0%

Flaky tests

6

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

9.80s

Response Time (max): 35.28s

Response Time (total): 156.75s

Wrong answer: 4 API error: 2 Extra formatting: 2 Did not follow instructions: 2

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#80 Grok 4.20 Multi Agent Beta

medium
Cost
$0.261
Time
123.4s
Tokens
199,344 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-05-06 14:16 Re-test 4.8 N/A $5.599 ↑ Compare
2026-05-06 14:16 Re-test 4.8 N/A $5.599 ↑ Compare
2026-05-06 14:16 Re-test 6.6 N/A $5.599 ↑ Compare
2026-05-06 14:16 Re-test 6.6 N/A $5.074 Compare
2026-05-06 14:16 Suite changed 6.6 N/A $5.074 Current run
2026-04-11 01:19 First recorded run 6.4 N/A $5.074 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Run comparison

RunBenchmark coverageScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-05-06 14:16 · Suite changed52/54 attempts6.67.4N/A8/186608,7040$5.0749.80s
2026-05-06 14:16 · Re-test52/54 attempts6.67.9N/A8/185600,042721,952$5.5999.69s
Difference—+0.1-0.50+1+8662-721952-$0.526+105ms

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 6.9 5.8
Coding 10.0 10.0
Combined 3.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 2.9 7.2
General Intelligence 5.8 2.8
Instructions following 9.8 10.0
Puzzle Solving 7.2 5.1
Tool Calling 3.0 10.0

Compared models