Skip to main content
leaderboard
.cn
Toggle Sidebar
Search models or organizations…
⌘K
Explore
Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio
Library
Models
Pricing
Organizations
Benchmarks
Data sources
Settings
Toggle Sidebar
leaderboard
.cn
Loading page content
Feedback
Loading page content
Back to models
Grok 4.5
Closed
Share
Add to comparison
Tool use · Reasoning
Overview
Pricing
Evaluations
Evaluation overview
Overall rank
#29
85.9 points · 212 models
Agents rank
#20
82.4 points · 159 models
Data coverage
30 items
11 sources · updated through 2026-09-02
Domain performance
Coding
#32 / 192
86.7
Research
#59 / 206
81.9
Agents
#20 / 159
82.4
Vision
#35 / 92
81.2
Long context
#25 / 98
86.5
Evaluation highlights
All evaluations
Arena Agent Tool Hallucination
Agents · Arena.ai Agent
1.33%
1
/ 52
Arena Text Rating
Reasoning · Arena.ai Text
1,470.43Elo
31
/ 375
Arena Vision Rating
Multimodal · Arena.ai Vision
1,285.02Elo
13
/ 133
Arena Image-to-WebDev Rating
Coding · Arena.ai Image-to-WebDev
1,580.44Elo
6
/ 36
MRCR v2 (8-needle 128K)
Long context · Google Gemini 3.6 Flash Official Release Evaluation
81.4%
6
/ 13
APEX-Agents
Agents · xAI Grok 4.6 Release
47.1%
4
/ 24
Basic information
Context (input / output)
500K / -
Release date
2026-07
Input modalities
Text
Output modalities
Text
API model ID
grok-4.5
Availability
xAI API
Full pricing
Input
$2 /1M
Output
$6 /1M
Related links
Official site
Version relationships
Grok 4 family
Grok 4 Fast
2025-09 · Same series · Deprecated
Grok 4.1
2025-11 · Same series
Grok 4.1 Fast
2025-11 · Same series · Deprecated
Grok 4.20
2026-03 · Same series
Grok 4.3
2026-06 · Same series
Grok 4.5
Current
2026-07 · Current model
Grok 4.6
2026-08 · Same series
Grok 4.7
2026-09 · Same series