Grok 3
xAI · Released Feb 17, 2025
$3
Input price / MTok
#23 of 27$15
Output price / MTok
#23 of 27131K
Context window
#25 of 2884.6
GPQA Diamond
#11 of 1993.3
AIME 2025
#3 of 1079.4
LiveCodeBench
#4 of 8Summary
Grok 3 is a proprietary language model from xAI, released on Feb 17, 2025.
At $3 input and $15 output per million tokens, it ranks #23 of 27 for input price, placing it mid-range on input cost.
Its context window of 131K tokens ranks #25 of 28 for context depth in this dataset.
It targets reasoning, coding workloads.
Trained with 10x compute of Grok 2 on the 200K-GPU Colossus cluster.
Benchmarks
| Benchmark | Score | Max | % | Rank | Source |
|---|---|---|---|---|---|
| GPQA Diamond | 84.6 | 100 | 84.6% | #11/19 | xAI (self-reported in official announcem... |
| AIME 2025 | 93.3 | 100 | 93.3% | #3/10 | xAI (self-reported in official announcem... |
| LiveCodeBench | 79.4 | 100 | 79.4% | #4/8 | xAI (self-reported in official announcem... |
Similar Models
Compare all 6 modelsModels with the most shared benchmark coverage and closest scores to Grok 3.
Grok 3
GPQA Diamond#11 of 19
Graduate-level science reasoningAIME 2025#3 of 10
Advanced math competition problemsLiveCodeBench#4 of 8
Live competitive programmingCompare Grok 3 side by side
Pre-filled with 5 similar models