xAI model product
Grok 4.1 Thinking
1, using thinking tokens for deeper reasoning.
Updated Sep 8, 2026. Default version: Grok-4.1 Thinking
LLMBoard Score48.0Grok-4.1 Thinking
Coverage0%2 benchmark families
Context window256KTokens
Official input priceN/AOfficial price unavailable
Grok 4.1 Thinking Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Grok 4.1 Thinking Benchmark Results
Benchmark scores for Grok-4.1 Thinking.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkBioLP-Bench | Score37.00% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkCloningScenarios | Score46.00% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkEQ-Bench | Score1,586.00 points | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkLMArena Text Leaderboard | Score1,483.00 points | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMASK | Score51.00% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkProtocolQA | Score79.00% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkVirology Capabilities Test | Score61.00% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkWMDP | Score84.00% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkCyBench | Score39.00% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkFigQA | Score34.00% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkCreative Writing v3 | Score86.10% | Rank04 | Participants13 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,465.46 rating | Rank36 | Participants210 | Percentile83.25% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,437.11 rating | Rank56 | Participants210 | Percentile73.68% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,433.73 rating | Rank72 | Participants121 | Percentile40.83% | EvidenceA | Evaluated |
| BenchmarkLM Arena Webdev | Score1,210.67 rating | Rank93 | Participants97 | Percentile4.17% | EvidenceA | Evaluated |
Grok 4.1 Thinking Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext style control | Categorypolish | Rank12 | Rating / score1,487.45 | Votes1,898 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank13 | Rating / score1,501.79 | Votes4,277 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank24 | Rating / score1,456.02 | Votes1,898 | ObservationsN/A | Result date |
| Arenatext factuality | Categorygerman | Rank24 | Rating / score1,412.44 | Votes593 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank25 | Rating / score1,464.87 | Votes1,904 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank26 | Rating / score1,429.74 | Votes1,106 | ObservationsN/A | Result date |
| Arenatext factuality | Categorypolish | Rank27 | Rating / score1,425.39 | Votes1,207 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank30 | Rating / score1,486.43 | Votes1,654 | ObservationsN/A | Result date |
| Arenatext factuality | Categorykorean | Rank31 | Rating / score1,385.66 | Votes545 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank32 | Rating / score1,476.36 | Votes4,726 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank34 | Rating / score1,463.55 | Votes1,133 | ObservationsN/A | Result date |
| Arenatext style control | Categorynon english | Rank34 | Rating / score1,453.26 | Votes36,815 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexclude ties | Rank35 | Rating / score1,472.93 | Votes47,377 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryspanish | Rank36 | Rating / score1,438.26 | Votes1,259 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank36 | Rating / score1,465.46 | Votes64,198 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank37 | Rating / score1,472.41 | Votes27,382 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry life and physical and social science | Rank38 | Rating / score1,479.56 | Votes10,672 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry business and management and financial operations | Rank40 | Rating / score1,459.83 | Votes12,365 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank40 | Rating / score1,434.02 | Votes12,258 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank40 | Rating / score1,495.61 | Votes22,901 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank40 | Rating / score1,459.66 | Votes7,463 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts | Rank43 | Rating / score1,476.74 | Votes36,950 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycreative writing | Rank46 | Rating / score1,423.46 | Votes6,208 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank47 | Rating / score1,440.12 | Votes1,133 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank47 | Rating / score1,397.25 | Votes1,106 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryfrench | Rank48 | Rating / score1,451.34 | Votes1,113 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank48 | Rating / score1,413.96 | Votes618 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry entertainment and sports and media | Rank49 | Rating / score1,418.81 | Votes8,269 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank49 | Rating / score1,498.70 | Votes14,835 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank49 | Rating / score1,427.47 | Votes9,716 | ObservationsN/A | Result date |
Grok 4.1 Thinking Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Grok 4.1 Thinking Runtime Performance
Provider-specific output speed and catalog latency for Grok-4.1 Thinking. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderxAI | Output Speed80.00 tok/s | Catalog Latency1.20 s | Max Input256K | Max Output8K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Grok 4.1 Thinking Specifications
Technical details for the model's default version.
- Version
- Grok-4.1 Thinking
- Released
- Nov 17, 2025
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 256K
- Max output
- 8K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Grok 4.1 Thinking Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGrok-4.1 Thinking | Released | LLMBoard48.01 | ParametersN/A | Context256K | Max output8K | Open weightsNo | LicenseProprietary |
Models similar to Grok 4.1 Thinking
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
XA
Grok 3 Mini
xAI
XA
Grok 4 Fast
xAI
XA
Grok 4.1
xAI
XA
Grok 3
xAI
XA
Grok 4
xAI
XA
Grok 4.20 Beta Reasoning
xAI
What is Grok 4.1 Thinking?
Key information about Grok 4.1 Thinking and its available data.
1. It includes training and safety measures focused on factual accuracy, helpfulness, alignment, refusal behavior, and reduced deception.
Data as of 2026-09-08.
FAQ
Common questions about Grok 4.1 Thinking.
When was Grok 4.1 Thinking released?
Grok 4.1 Thinking's default version was released on Nov 17, 2025.
How much does Grok 4.1 Thinking cost?
No official standard PAYG price is currently available for Grok 4.1 Thinking.
Who created Grok 4.1 Thinking?
Grok 4.1 Thinking was created by xAI.
What is the context window for Grok 4.1 Thinking?
The default version has a 256K token context window.
Is Grok 4.1 Thinking open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Grok 4.1 Thinking?
No provider offering is currently linked to the default version.