Grok 4.3 vs Claude 4.5 Haiku: Release Comparison
Comparison of the Grok 4.3 and Claude 4.5 Haiku releases: 4 and 2 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 6 models.
- For intelligence, Grok 4.3 scores highest: Grok 4.3 (high) at 25, against Claude 4.5 Haiku (Reasoning) at 18 for Claude 4.5 Haiku.
- For output speed, Grok 4.3 is fastest: Grok 4.3 (high) at 126 t/s, against Claude 4.5 Haiku (Non-reasoning) at 91 t/s for Claude 4.5 Haiku.
- For cost per task, Grok 4.3 is cheapest: Grok 4.3 (Non-reasoning) at $0.14, against Claude 4.5 Haiku (Reasoning) at $0.21 for Claude 4.5 Haiku.
Releases compared
Intelligence
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Intelligence Index Task
Cost
Cost per Intelligence Index Task
Speed & Latency
Output Speed
Capability Scores
Capability Indices
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2, AA-Briefcase, Terminal-Bench 4.0 · Higher is better
Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2, AA-Briefcase, AA-LCR v1.1 · Higher is better
Further details
Input modality | Output modality | Weights | Provider Benchmarks | ||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Grok 4.3 (high) |  SpaceXAI | 25 | 28 | 18 | 33 | 27 | 31 | 41 | $0.17 | $0.6 | $1.25 | $2.50 | $0.20 | $332 | 18k | 11k | 87M | 126 | 20.57s | 20.57s | 24.56s | 143.84s | - | 1M | Apr 2026 | - | Yes | Supports: text and image | Supports: text | Not available | - |   | |
| Grok 4.3 (medium) | SpaceXAI | 25 | - | - | - | - | - | - | - | $0.6 | $1.25 | $2.50 | $0.20 | - | - | - | - | 108 | 12.57s | 12.57s | 17.20s | - | - | 1M | Apr 2026 | - | Yes | Supports: text and image | Supports: text | Not available | - | | |
| Grok 4.3 (low) | SpaceXAI | 24 | - | - | - | - | - | - | - | $0.6 | $1.25 | $2.50 | $0.20 | - | - | - | - | 101 | 4.55s | 4.55s | 9.47s | - | - | 1M | Apr 2026 | - | Yes | Supports: text and image | Supports: text | Not available | - | | |
| Claude 4.5 Haiku (Reasoning) |  Anthropic | 18 | 16 | 11 | 20 | 17 | 20 | 27 | $0.21 | $0.8 | $1.00 | $5.00 | $0.10 | $524 | 18k | 8k | 78M | 89 | 18.59s | 18.59s | 24.19s | 160.56s | - | 200k | Oct 2025 | Jul 2025 | Yes | Supports: text and image | Supports: text | Not available | - |  | |
| Claude 4.5 Haiku (Non-reasoning) | Anthropic | 15 | - | - | - | - | - | - | - | $0.8 | $1.00 | $5.00 | $0.10 | - | - | - | - | 91 | 0.66s | 0.66s | 6.19s | - | - | 200k | Oct 2025 | Jul 2025 | No | Supports: text and image | Supports: text | Not available | - | | |
| Grok 4.3 (Non-reasoning) | SpaceXAI | 15 | 16 | 14 | 19 | - | 15 | 21 | $0.14 | $0.6 | $1.25 | $2.50 | $0.20 | $203 | 9k | 0 | 12M | 106 | 0.84s | 0.84s | 5.57s | 89.70s | - | 1M | Apr 2026 | - | No | Supports: text and image | Supports: text | Not available | - | | |