Compare AI models
| These models have no shared benchmark scores. | ||
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | — | 50% |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | — | 35% |
| Overview | ||
| Company | SpaceXSI | SpaceXSI |
| Release date | Aug 23 2025 | Apr 17 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Grok 2.5vsClaude Fable 5.2Grok 4.3 BetavsClaude Fable 5.2Grok 2.5vsGPT-6.1 TerraGrok 4.3 BetavsGPT-6.1 TerraGrok 2.5vsGemini 4 CarbonGrok 4.3 BetavsGemini 4 CarbonGrok 2.5vsMuse EmberGrok 4.3 BetavsMuse EmberGrok 2.5vsDeepSeek-V4.1-Flash-1017Grok 4.3 BetavsDeepSeek-V4.1-Flash-1017Grok 2.5vsMistral Large 4Grok 4.3 BetavsMistral Large 4Frequently asked questions
Grok 2.5 and Grok 4.3 Beta don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Grok 2.5 shipped 237 days before Grok 4.3 Beta, so benchmark comparisons should account for the intervening progress.
Grok 2.5 is open weight, while Grok 4.3 Beta is closed.
Direct benchmark comparisons are unavailable — Grok 2.5 and Grok 4.3 Beta don't publish scores on any of the same benchmarks.