Compare AI models
These models have no shared benchmark scores. | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 40.4% | — |
| Overview | ||
| Company | Anthropic | SpaceXAI |
| Release date | Mar 4 2024 | Nov 3 2023 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude 3 SonnetvsGPT-6.1 SolGrok‑1vsGPT-6.1 SolClaude 3 SonnetvsGemini 4 ArgonGrok‑1vsGemini 4 ArgonClaude 3 SonnetvsMuse Spark 1.3Grok‑1vsMuse Spark 1.3Claude 3 SonnetvsDeepSeek-V4.1-FlashGrok‑1vsDeepSeek-V4.1-FlashClaude 3 SonnetvsMistral Large 4Grok‑1vsMistral Large 4Claude 3 SonnetvsKimi K3Grok‑1vsKimi K3Frequently asked questions
Claude 3 Sonnet and Grok‑1 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Grok‑1 shipped 122 days before Claude 3 Sonnet, so benchmark comparisons should account for the intervening progress.
Claude 3 Sonnet is closed, while Grok‑1 is open weight.
Direct benchmark comparisons are unavailable — Claude 3 Sonnet and Grok‑1 don't publish scores on any of the same benchmarks.