Grok 4.5 (high)
SpaceXAIGrok
Release Date
2026-07-08
Parameters
—
Context Length
500K
Modalities
image, text
Capability Radar
40
general
70
coding
93
reasoning
69
scienceest.
40
agents
80
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 8 | 93.0 | AA |
| Science | 9 | 88.0 | AA |
Benchmark Scores (LLM Stats)
Agents
BrowseComp
44.9%SR
Biology
GPQA
85.7%SR
Code
LiveCodeBench
80.0%SR
Factuality
SimpleQA
95.0%SR
Math
HMMT 2025
93.3%SR
AIME 2025
92.0%SR
Humanity's Last Exam
20.0%SR
AA Evaluation Indices
Coding Index72.4
Gpqa0.9
Terminalbench V2 10.8
Lcr0.7
Scicode0.5
Hle0.4
Tau Banking0.3
LLM Stats Category Scores
Physics90
Factuality90
General90
Biology90
Chemistry90
Code80
Math70
Reasoning70
Search40
Agents40
Vision20
Pricing
Input Price$2 / 1M tokens
Output Price$6 / 1M tokens
Blended Price (3:1)$3 / 1M tokens
Cache Read Price$0.5 / 1M tokens
Speed
Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s
Provider Price Ranking
Provider Price Ranking
3 providers
Cheapest: SpaceXAIMost Expensive: Venice AI
ProviderInputOutput
1SpaceXAIPRIMARY
$2
$6
2xAI
$2
$6
3Venice AI
$2.27
$6.8
Compare pricing across different API providers for this model.