Grok 4.3 vs Claude Sonnet 4.6: Release Comparison
Comparison of the Grok 4.3 and Claude Sonnet 4.6 releases: 4 and 3 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 7 models.
- For intelligence, Claude Sonnet 4.6 scores highest: Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) at 30, against Grok 4.3 (high) at 25 for Grok 4.3.
- For output speed, Grok 4.3 is fastest: Grok 4.3 (high) at 114 t/s, against Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) at 45 t/s for Claude Sonnet 4.6.
- For cost per task, Grok 4.3 is cheapest: Grok 4.3 (Non-reasoning) at $0.14, against Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) at $2.49 for Claude Sonnet 4.6.
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 | ||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) |  Anthropic | 30 | 34 | 31 | 38 | 32 | 32 | 43 | $2.49 | $2.3 | $3.00 | $15.00 | $0.30 | $4,925 | 75k | 56k | 233M | 45 | 129.84s | 129.84s | 140.84s | 1501.35s | - | 1M | Feb 2026 | - | Yes | Supports: text and image | Supports: text | Not available | - |    | |
| 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 | 114 | 18.32s | 18.32s | 22.71s | 155.89s | - | 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 | 17.21s | - | - | 1M | Apr 2026 | - | Yes | Supports: text and image | Supports: text | Not available | - | | |
| Claude Sonnet 4.6 (Non-reasoning, High Effort) | Anthropic | 25 | - | - | - | - | - | - | - | $2.3 | $3.00 | $15.00 | $0.30 | - | - | - | - | 40 | 1.32s | 1.32s | 13.69s | - | - | 1M | Feb 2026 | - | No | Supports: text and image | Supports: text | Not available | - | | |
| Grok 4.3 (low) | SpaceXAI | 24 | - | - | - | - | - | - | - | $0.6 | $1.25 | $2.50 | $0.20 | - | - | - | - | 102 | 4.55s | 4.55s | 9.43s | - | - | 1M | Apr 2026 | - | Yes | Supports: text and image | Supports: text | Not available | - | | |
| Claude Sonnet 4.6 (Non-reasoning, Low Effort) | Anthropic | 23 | - | - | - | - | - | - | - | $2.3 | $3.00 | $15.00 | $0.30 | - | - | - | - | 40 | 1.41s | 1.41s | 14.00s | - | - | 1M | Feb 2026 | - | 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 | 108 | 0.70s | 0.70s | 5.32s | 86.55s | - | 1M | Apr 2026 | - | No | Supports: text and image | Supports: text | Not available | - | | |