GeekRadar / The comparison desk

COMPARE.

AI models

xai

Grok 4.20

AI model Released Feb 17, 2026

API mode: Chat^*
Maximum output: 1,000,000 tokens^*

Capability & preference

General capability · ECI

A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.

Grok 4.20 152.3^* Grok 4.20 · 95% interval 149.5–154.7

Model performance

Radar task score: four tests, equal weight. An experimental summary of these tasks, not a universal intelligence rating.

Grok 4.20

Tested configuration Radar task score

Unrated

3/4 core tests · not enough evidence

5 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

Expert-written science questions; strict multiple-choice scoring. Chance accuracy is 25%.

Grok 4.20 89.3^*% Approx. 95% interval: 85.7–93.0% · 2026-07-13

Novel problem solving

Mystery Game Puzzles · 25%

Best-next-move puzzles in an undisclosed game variant. A narrow reasoning test, not general intelligence.

Grok 4.20 Not available

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

Private v2 mathematics problems with Python tools. Earlier versions and Tier 4 are excluded.

Grok 4.20 44.9^*% Approx. 95% interval: 39.1–50.7% · 2026-07-13

Factual answers

SimpleQA Verified · 25%

Correct factual answers under a guessing prompt, graded by a model. Not a hallucination or abstention score.

Grok 4.20 30.2^*% Approx. 95% interval: 27.4–33.0% · 2026-08-27

Competition mathematics

OTIS Mock AIME 2024-2025 · Separate result

Competition problems with model-extracted answers checked against an exact key. Earlier grading procedures are excluded.

Grok 4.20 92.2^*% Approx. 95% interval: 85.8–98.7% · 2026-07-13

Research mathematics

FrontierMath Tier 4 v2 · Separate result

The hardest private FrontierMath problems, corrected v2 set, with Python tools. Separate from Tiers 1-3 in the core score.

Grok 4.20 17.1^*% Approx. 95% interval: 5.4–28.7% · 2026-07-13

Bars show reported task scores. Whiskers are approximate 95% intervals where standard errors are available. Different reasoning budgets are not equal-cost tests. Missing results are never zero.

Run it locally

Inference · memory estimate

Grok 4.20

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Maximum input: 1,000,000 tokens^*
Maximum output: 1,000,000 tokens^*
Reasoning: Yes^*
Tool calling: Yes^*
Structured output: Yes^*
API mode: Chat^*
Image input: Yes^*
Prompt caching: Yes^*
Tool choice: Yes^*
Web search: Yes^*

System configuration

Detailed specifications

Specifications · 25 fields

cache read input token cost

2.0e-7^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache read input token cost above 200k tokens

4.0e-7^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache read input token cost above 200k tokens batches

3.2e-7^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache read input token cost batches

1.6e-7^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per image token

1.25e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token

1.25e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token above 200k tokens

2.5e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token above 200k tokens batches

2.0e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token batches

1.0e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

litellm provider

xai^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

max input tokens

1,000,000^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

max output tokens

1,000,000^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

max tokens

1,000,000^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

mode

chat^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output cost per token

2.5e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output cost per token above 200k tokens

5.0e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output cost per token above 200k tokens batches

4.0e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output cost per token batches

2.0e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports function calling

Yes^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports prompt caching

Yes^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports reasoning

Yes^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports response schema

Yes^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports tool choice

Yes^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports vision

Yes^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports web search

Yes^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.20^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

* Provisional data