Model vs model

Grok 4.20 vs A.X-K2

A debate-ready pair page: current winner, strongest alternative, decisive benchmarks, and the warning that should travel with the claim.

Use case · Everyday chatbot
Winner · Grok 4.20
Sources · All public sources

Winner

Grok 4.20

xAI

8benchmarks won

Reasoning / math / science
Coding

Versus · Everyday chatbot

Grok 4.20 leads this compare set for everyday chatbot.

Grok 4.208 of 8 wins

Thin verified coverage

0 shared benchmarks are still too close to call, so the win stays conditional. This compare uses all public sources, with provider-official evidence labeled separately.

Close calls: 0
Sources: All public

Full compare workspace Disagreement page

100%win share

Challenger

A.X-K2

Unknown

0benchmarks won

Chat / text
Reasoning / math / science

The cases in full

Grok 4.20 case

Reasoning / math / science
Coding

A.X-K2 case

Chat / text
Reasoning / math / science

What changes the outcome

Grok 4.20: 80 visible benchmark gaps still leave room for the result to move.
A.X-K2: 126 visible benchmark gaps still leave room for the result to move.

Why this result is surprising

The visible shared evidence is more decisive than usual for this compare set.
Very few shared benchmarks are decisively separating these models.

Why this is not a clean win

0 shared benchmarks are still too close to call, so the win stays conditional. This compare uses all public sources, with provider-official evidence labeled separately.
A.X-K2 remains the strongest alternative once you change use case, mode, or missing-evidence assumptions.

Open full compare workspace Open evidence page Open disagreement page

Decisive benchmarks

8 of 138 benchmarks


Intelligence Index AA · index Text · Chat / text	2269% exact aliasverified runtime Row details Raw value 22 Percentile 69% Last updated recent Eligibility headline eligible Identity provider alias (0.94) Source label Grok 4.20 0309 v2 (Non-reasoning) Source row	35n/a exact aliasverified runtimeContext only Row details Raw value 35 Percentile n/a Last updated recent Eligibility benchmark_derived_model Identity provider alias (0.94) Source label A.X-K2 Source row	n/a
GPQA AA · % Text · Reasoning / math / science	77.6%73.8% exact aliasverified runtime Row details Raw value 77.6% Percentile 73.8% Last updated recent Eligibility headline eligible Identity provider alias (0.94) Source label Grok 4.20 0309 v2 (Non-reasoning) Source row	85.7%n/a exact aliasverified runtimeContext only Row details Raw value 85.7% Percentile n/a Last updated recent Eligibility benchmark_derived_model Identity provider alias (0.94) Source label A.X-K2 Source row	n/a
Humanity's Last Exam AA · % Text · Reasoning / math / science	27.9%88.7% exact aliasverified runtime Row details Raw value 27.9% Percentile 88.7% Last updated recent Eligibility headline eligible Identity provider alias (0.94) Source label Grok 4.20 0309 v2 (Non-reasoning) Source row	29.6%n/a exact aliasverified runtimeContext only Row details Raw value 29.6% Percentile n/a Last updated recent Eligibility benchmark_derived_model Identity provider alias (0.94) Source label A.X-K2 Source row	n/a
CritPt AA · % Text · Reasoning / math / science	0.3%70% exact aliasverified runtime Row details Raw value 0.3% Percentile 70% Last updated recent Eligibility headline eligible Identity provider alias (0.94) Source label Grok 4.20 0309 v2 (Non-reasoning) Source row	8.9%n/a exact aliasverified runtimeContext only Row details Raw value 8.9% Percentile n/a Last updated recent Eligibility benchmark_derived_model Identity provider alias (0.94) Source label A.X-K2 Source row	n/a
SciCode AA · % Code · Coding	32.8%54.3% exact aliasverified runtime Row details Raw value 32.8% Percentile 54.3% Last updated recent Eligibility headline eligible Identity provider alias (0.94) Source label Grok 4.20 0309 v2 (Non-reasoning) Source row	38.5%n/a exact aliasverified runtimeContext only Row details Raw value 38.5% Percentile n/a Last updated recent Eligibility benchmark_derived_model Identity provider alias (0.94) Source label A.X-K2 Source row	n/a
AA-Omniscience accuracy AA · % Text · Chat / text	26.7%79.2% exact aliasverified runtime Row details Raw value 26.7% Percentile 79.2% Last updated recent Eligibility headline eligible Identity provider alias (0.94) Source label Grok 4.20 0309 v2 (Non-reasoning) Source row	18.6%n/a exact aliasverified runtimeContext only Row details Raw value 18.6% Percentile n/a Last updated recent Eligibility benchmark_derived_model Identity provider alias (0.94) Source label A.X-K2 Source row	n/a
AA-Omniscience non-hallucination AA · % Text · Chat / text	2.7%2.2% exact aliasverified runtime Row details Raw value 2.7% Percentile 2.2% Last updated recent Eligibility headline eligible Identity provider alias (0.94) Source label Grok 4.20 0309 v2 (Non-reasoning) Source row	67%n/a exact aliasverified runtimeContext only Row details Raw value 67% Percentile n/a Last updated recent Eligibility benchmark_derived_model Identity provider alias (0.94) Source label A.X-K2 Source row	n/a
Long Context Reasoning AA · % Document · Long context	20.7%35.2% exact aliasverified runtime Row details Raw value 20.7% Percentile 35.2% Last updated recent Eligibility headline eligible Identity provider alias (0.94) Source label Grok 4.20 0309 v2 (Non-reasoning) Source row	66%n/a exact aliasverified runtimeContext only Row details Raw value 66% Percentile n/a Last updated recent Eligibility benchmark_derived_model Identity provider alias (0.94) Source label A.X-K2 Source row	n/a

1-8 of 8

Page 1 of 1Page size

Intelligence Index

AA · index

Text · Chat / text

2269%

exact aliasverified runtime

Row details

Raw value: 22
Percentile: 69%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)
Source label: Grok 4.20 0309 v2 (Non-reasoning)

Source row

35n/a

exact aliasverified runtimeContext only

Row details

Raw value: 35
Percentile: n/a
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)
Source label: A.X-K2

Source row

n/a

GPQA

AA · %

Text · Reasoning / math / science

77.6%73.8%

exact aliasverified runtime

Row details

Raw value: 77.6%
Percentile: 73.8%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)
Source label: Grok 4.20 0309 v2 (Non-reasoning)

Source row

85.7%n/a

exact aliasverified runtimeContext only

Row details

Raw value: 85.7%
Percentile: n/a
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)
Source label: A.X-K2

Source row

n/a

Humanity's Last Exam

AA · %

Text · Reasoning / math / science

27.9%88.7%

exact aliasverified runtime

Row details

Raw value: 27.9%
Percentile: 88.7%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)
Source label: Grok 4.20 0309 v2 (Non-reasoning)

Source row

29.6%n/a

exact aliasverified runtimeContext only

Row details

Raw value: 29.6%
Percentile: n/a
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)
Source label: A.X-K2

Source row

n/a

CritPt

AA · %

Text · Reasoning / math / science

0.3%70%

exact aliasverified runtime

Row details

Raw value: 0.3%
Percentile: 70%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)
Source label: Grok 4.20 0309 v2 (Non-reasoning)

Source row

8.9%n/a

exact aliasverified runtimeContext only

Row details

Raw value: 8.9%
Percentile: n/a
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)
Source label: A.X-K2

Source row

n/a

SciCode

AA · %

Code · Coding

32.8%54.3%

exact aliasverified runtime

Row details

Raw value: 32.8%
Percentile: 54.3%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)
Source label: Grok 4.20 0309 v2 (Non-reasoning)

Source row

38.5%n/a

exact aliasverified runtimeContext only

Row details

Raw value: 38.5%
Percentile: n/a
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)
Source label: A.X-K2

Source row

n/a

AA-Omniscience accuracy

AA · %

Text · Chat / text

26.7%79.2%

exact aliasverified runtime

Row details

Raw value: 26.7%
Percentile: 79.2%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)
Source label: Grok 4.20 0309 v2 (Non-reasoning)

Source row

18.6%n/a

exact aliasverified runtimeContext only

Row details

Raw value: 18.6%
Percentile: n/a
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)
Source label: A.X-K2

Source row

n/a

AA-Omniscience non-hallucination

AA · %

Text · Chat / text

2.7%2.2%

exact aliasverified runtime

Row details

Raw value: 2.7%
Percentile: 2.2%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)
Source label: Grok 4.20 0309 v2 (Non-reasoning)

Source row

67%n/a

exact aliasverified runtimeContext only

Row details

Raw value: 67%
Percentile: n/a
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)
Source label: A.X-K2

Source row

n/a

Long Context Reasoning

AA · %

Document · Long context

20.7%35.2%

exact aliasverified runtime

Row details

Raw value: 20.7%
Percentile: 35.2%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)
Source label: Grok 4.20 0309 v2 (Non-reasoning)

Source row

66%n/a

exact aliasverified runtimeContext only

Row details

Raw value: 66%
Percentile: n/a
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)
Source label: A.X-K2

Source row

n/a

Grok 4.20 vs A.X-K2

Grok 4.20

Grok 4.20 leads this compare set for everyday chatbot.

A.X-K2

Grok 4.20 case

A.X-K2 case

What changes the outcome

Why this result is surprising

Why this is not a clean win

Share the recommendation with the source data attached.

Open or copy the stable surfaces

Use the exact public framing

Pick the voice before you post

Compose a post that keeps the warning attached

Decisive benchmarks

Loading model comparison.

Grok 4.20 vs A.X-K2

Grok 4.20

Grok 4.20 leads this compare set for everyday chatbot.

A.X-K2

Grok 4.20 case

A.X-K2 case

What changes the outcome

Why this result is surprising

Why this is not a clean win

Share the recommendation with the source data attached.

Open or copy the stable surfaces

Use the exact public framing

Pick the voice before you post

Compose a post that keeps the warning attached

Decisive benchmarks