xAI model product
Grok 3
Grok 3, launched by xAI on February 17, 2025, is an advanced AI model with significantly enhanced capabilities compared to Grok 2, boasting an order of magnitude increase in performance.
Updated Aug 12, 2026. Default version: Grok-3
LLMBoard score54.8Grok-3
Coverage60%5 benchmark families
Context window128KTokens
Official input priceN/AOfficial price unavailable
Grok 3 Specifications
Technical details for the model's default version.
- Version
- Grok-3
- Released
- Feb 17, 2025
- Knowledge cutoff
- Nov 17, 2024
- Parameters
- N/A
- Context window
- 128K
- Max output
- 8K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Grok 3 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Grok 3 Benchmark Results
Benchmark scores for Grok-3.
| AIME 2024 | 93.3% | 03 | 53 | 96.2% | C | |
| LiveCodeBench | 79.4% | 10 | 73 | 87.5% | C | |
| MMMU | 78.0% | 17 | 63 | 74.2% | C | |
| AIME 2025 | 93.3% | 29 | 114 | 75.2% | C | |
| GPQA | 84.6% | 56 | 234 | 76.4% | C |
Grok 3 Arena Results
Preference and agent-evaluation results for the default version.
| text | overall | 83 | 1425.1 | 32,943 | N/A | |
| text style control | overall | 125 | 1411.4 | 32,943 | N/A |
Grok 3 Runtime Performance
Provider-specific output speed and catalog latency for Grok-3. Runtime does not affect the capability score.
| xAI | 100 tok/s | 0.7 s | 128K | 8K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Grok 3 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $3 input, $15 output per 1M via Poe
- Tracked offerings
- 2
| Poe | xai/grok-3 | global | $3 | $15 | 131.1K | |
| Helicone | grok-3 | global | $3 | $15 | 131.1K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Grok 3 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Grok-3 | 54.8 | N/A | 128K | 8K | No | Proprietary |
What is Grok 3?
Key information about Grok 3 and its available data.
Grok 3, launched by xAI on February 17, 2025, is an advanced AI model with significantly enhanced capabilities compared to Grok 2, boasting an order of magnitude increase in performance.
Trained on a vast dataset that includes legal documents among others, and utilizing a massive compute infrastructure with around 200,000 GPUs in a Memphis data center, Grok 3's training used ten times more compute than its predecessor.
It features specialized models like Grok 3 Reasoning and Grok 3 Mini Reasoning for complex problem-solving, and it excels in benchmarks like AIME for mathematics and GPQA for PhD-level science.
Data as of 2026-08-11.
Grok 3 vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Grok 3
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
XA
Grok 4 Fast
xAI
XA
Grok 4
xAI
XA
Grok 4.20 Beta Reasoning
xAI
XA
Grok 4.1 Thinking
xAI
XA
Grok 3 Mini
xAI
XA
Grok 4.1
xAI
FAQ
Common questions about Grok 3.
When was Grok 3 released?
Grok 3's default version was released on Feb 17, 2025.
How much does Grok 3 cost?
No official standard PAYG price is currently available for Grok 3. The lowest tracked third-party offer starts at $3 input and $15 output via Poe.
Who created Grok 3?
Grok 3 was created by xAI.
What is the context window for Grok 3?
The default version has a 128K token context window.
Is Grok 3 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Grok 3?
2 provider offerings are linked to the default version.
What models should I compare Grok 3 with?
Nearby ranked alternatives include MiniMax M2.5, Qwen3.6 35B A3B, MAI Thinking 1.