Capability
53.9/100
field median 57.2
#97 of 215 ranked models
Model profile · xAI
Grok 4.20
Grok 4.20 scores 53.9 out of 100 and ranks #97 of 215. This profile shows 18 source-displayable benchmark rows; its strongest eligible category is Multimodal & Grounded at #28. API pricing is $2 input and $6 output per million tokens.
Data as of July 28, 2026 · How the score is built
Strongest published evidence
Multimodal & Grounded ranks #28. Particularly strong for screenshots, documents, charts, and grounded multimodal workflows.
Validate before choosing
18 published rows leave some tracked benchmark slots empty. Coding is its lowest eligible category at #86.
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Price
$2input / $6 output
input median $1
blended $4
Speed
233tok/s
field median 107 tok/s
First token 10.33 s
Context
2Mtokens
field median 256,000
Reported for this model; direct source link not stored
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
Grok 4.20 category percentile values
- Agentic60th percentile
- Coding34th percentile
- ReasoningNot eligible
- KnowledgeNot eligible
- MathNot eligible
- MultilingualNot eligible
- Multimodal13th percentile
- Instruction followingNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#52/129
- Coding#86/130
- ReasoningNot ranked
- KnowledgeNot ranked
- MathNot ranked
- MultilingualNot ranked
- Multimodal#28/32
- Inst. FollowingNot ranked
Top decileTop quartileMid-fieldNot eligible
What it costs to get this score
Published API price against the public score. The x-axis uses a log scale; the dashed path marks models that are not beaten by a cheaper, higher-scoring option. Price uses average of published input and output rates.
The chart opens on the current model. Scroll horizontally to inspect the full price axis.
Current modelGrok 4.20 · 53.9 score · $4 blended per million tokens
Horizontal: blended price per million tokens, log scale · Vertical: public score
How much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic1/3 verified
- Coding1/4 verified
- Reasoning1/2 verified
- Knowledge0/4 verified
- MathNot measured
- MultilingualNot measured
- Multimodal0/5 verified
- Inst. FollowingNot measured
Verified sourceProvisionalNot measured
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not published
- Context window
- 2M
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not disclosed by the provider
- Availability
- Not sourced yet
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing record
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #52 of 129Percentile 60thWeight 22%3 benchmarksMixed sources | 49.0 | #52 of 129 | 60th | 22% | 3 benchmarks | Mixed sources |
| CodingRank #86 of 130Percentile 34thWeight 20%4 benchmarksMixed sources | 46.0 | #86 of 130 | 34th | 20% | 4 benchmarks | Mixed sources |
| ReasoningRank Not rankedWeight 17%2 benchmarksMixed sources | 61.7 | Not ranked | Not available | 17% | 2 benchmarks | Mixed sources |
| KnowledgeWeight 12%4 benchmarksReported | Score pending | Not ranked | Not available | 12% | 4 benchmarks | Reported |
| MathWeight 5%0 benchmarksNot measured | Not measured | Not ranked | Not available | 5% | 0 benchmarks | Not measured |
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | Not ranked | Not available | 7% | 0 benchmarks | Not measured |
| MultimodalRank #28 of 32Percentile 13thWeight 12%5 benchmarksReported | 35.9 | #28 of 32 | 13th | 12% | 5 benchmarks | Reported |
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | Not ranked | Not available | 5% | 0 benchmarks | Not measured |
Benchmark ledger
Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Coding4 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | Score76.7% | Versus best verified row Best verified: Claude Opus 5 · 96% | Gap19.3 behind | WeightWeighted 16% | Secondary exact |
| SWE-bench Pro | Score51.8% | Versus best verified row Best verified: Claude Mythos 5 · 80.3% | Gap28.5 behind | WeightWeighted 10% | Secondary exact |
| LiveCodeBench Pro | Score74.2% | Versus best verified row Best verified: Sakana Fugu-Ultra · 90.8% | Gap16.6 behind | WeightDisplay only | Secondary exact |
| Vibe Code BenchVibe Code Bench v1.1 | Score4.06% | Versus best verified row Best verified: Claude Opus 4.7 · 71.00% | Gap66.9 behind | WeightDisplay only | Benchmark exact |
Agentic3 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Terminal-Bench 2.0 | Score47.1% | Versus best verified row Best verified: GPT-5.6 Sol · 91.9% | Gap44.8 behind | WeightWeighted 38% | Secondary exact |
| DeepSearchQA | Score62.8% | Versus best verified row Best verified: Claude Opus 5 · 95.0% | Gap32.2 behind | WeightDisplay only | Secondary exact |
| Gert LabsGert Labs Composite Game Benchmark | Score38.36% | Versus best verified row Best verified: Claude Opus 4.8 · 72.97% | Gap34.6 behind | WeightDisplay only | Benchmark exact |
Reasoning2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| ARC-AGI-2Abstraction and Reasoning Corpus for AGI v2 | Score53.3% | Versus best verified row Best verified: GPT-5.6 Sol · 92.5% | Gap39.2 behind | WeightWeighted 31% | Secondary exact |
| ARC-AGI-3Abstraction and Reasoning Corpus for AGI v3 | Score0.1% | Versus best verified row Best verified: Claude Opus 5 · 30.2% | Gap30.1 behind | WeightDisplay only | Benchmark exact |
Knowledge4 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| GPQA-DGPQA Diamond | Score88.5% | Versus best verified row Best verified: Sakana Fugu-Ultra · 95.5% | Gap7 behind | WeightDisplay only | Secondary exact |
| HLE w/o toolsHumanity's Last Exam without tools | Score31.6% | Versus best verified row Best verified: Claude Mythos 5 · 59% | Gap27.4 behind | WeightDisplay only | Secondary exact |
| HealthBench Hard | Score20.3% | Versus best verified row Best verified: Muse Spark · 42.8% | Gap22.5 behind | WeightDisplay only | Secondary exact |
| MedXpertQA (Text)MedXpertQA Text | Score50.2% | Versus best verified row Best verified: Muse Spark · 52.6% | Gap2.4 behind | WeightDisplay only | Secondary exact |
Multimodal5 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| MMMU-ProMassive Multi-discipline Multimodal Understanding Pro | Score75.2% | Versus best verified row Best verified: GPT-5.4 Pro · 94% | Gap18.8 behind | WeightWeighted 45% | Secondary exact |
| CharXivCharXiv Reasoning | Score60.9% | Versus best verified row Best verified: Claude Mythos 5 · 93.5% | Gap32.6 behind | WeightWeighted 25% | Secondary exact |
| ERQA | Score54.1% | Versus best verified row Best verified: Qwen3.7 Plus · 69.8% | Gap15.7 behind | WeightDisplay only | Secondary exact |
| SimpleVQA | Score57.4% | Versus best verified row Best verified: Qwen3.7 Plus · 81.7% | Gap24.3 behind | WeightDisplay only | Secondary exact |
| MedXpertQA (MM)MedXpertQA Multimodal | Score65.8% | Versus best verified row Best verified: Muse Spark · 78.4% | Gap12.6 behind | WeightDisplay only | Secondary exact |
Lineage
The sequence follows explicit supersedes links. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Nov 17, 2025
Grok 4.1Score 59.2 · Price not listed
Mar 10, 2026 · you are here
Grok 4.20Score 53.9 · $2 / $6
Reasoning
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
Grok 4.20 ranks #97 of 215 on the public leaderboard with a score of 53.88/100. It does not yet have enough sourced coverage for a verified position.
Grok 4.20 is a proprietary model with a 2M context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Tracked as unresolved. xAI's current docs now present this model as Grok 4.20, but a clean exact-value benchmark table is still missing. BenchLM also stores secondary exact values from Meta AI's April 8, 2026 comparison chart, which labels the same family as Grok 4.2 Reasoning.
Grok 4.20 sits in the Grok 4.20 family with Grok 4.20 Multi-agent. Its explicit predecessor is Grok 4.1. 18 of 369 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Multimodal & Grounded at #28, while its lowest eligible position is Coding at #86. particularly strong for screenshots, documents, charts, and grounded multimodal workflows.
Frequently asked questions
How does Grok 4.20 perform overall in AI benchmarks?
Grok 4.20 ranks #97 out of 215 models on the public BenchAlign leaderboard, with a score of 53.88/100. Its evidence status is Estimated, and this profile shows 18 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is Grok 4.20 good for knowledge and understanding?
Grok 4.20 has source-displayable benchmark coverage for knowledge and understanding, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Grok 4.20 good for coding and programming?
Grok 4.20 ranks #86 out of 130 eligible models for coding and programming, with a public category score of 46/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Grok 4.20 good for reasoning and logic?
Grok 4.20 has source-displayable benchmark coverage for reasoning and logic, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Grok 4.20 good for agentic tool use and computer tasks?
Grok 4.20 ranks #52 out of 129 eligible models for agentic tool use and computer tasks, with a public category score of 49/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Grok 4.20 good for multimodal and grounded tasks?
Grok 4.20 ranks #28 out of 32 eligible models for multimodal and grounded tasks, with a public category score of 35.9/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Which sibling models are related to Grok 4.20?
Grok 4.20 belongs to the Grok 4.20 family. Related tracked variants include Grok 4.20 Multi-agent. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does Grok 4.20 have full benchmark coverage on BenchLM?
No. Grok 4.20 currently has 19 source-displayable rows across 369 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Grok 4.20?
Grok 4.20 has a reported context window of 2M in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.
Last updated July 28, 2026. Runtime fields remain blank until a sourced snapshot exists.
Make the right model choice this week
The model to choose, the cheaper alternative, and the release we would wait on.