Compare AI models
| Benchmarks | ||
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. | 48% | 19% |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 76.2% | — |
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | 52% | — |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | 31.1% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 91.9% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 81% | — |
| Overview | ||
| Company | SpaceXAI | |
| Release date | Nov 18 2025 | Nov 19 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Gemini 3.0 ProvsClaude Sonnet 5.5Grok 4.1 FastvsClaude Sonnet 5.5Gemini 3.0 ProvsGPT-6.1 SolGrok 4.1 FastvsGPT-6.1 SolGemini 3.0 ProvsMuse Spark 1.3Grok 4.1 FastvsMuse Spark 1.3Gemini 3.0 ProvsDeepSeek-V4.1-FlashGrok 4.1 FastvsDeepSeek-V4.1-FlashGemini 3.0 ProvsMistral Large 4Grok 4.1 FastvsMistral Large 4Gemini 3.0 ProvsKimi K3Grok 4.1 FastvsKimi K3Frequently asked questions
Gemini 3.0 Pro leads Grok 4.1 Fast on 1 of the 1 benchmark they both report (BullshitBench v2). Gemini 3.0 Pro shipped 1 days before Grok 4.1 Fast, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On BullshitBench v2, Gemini 3.0 Pro leads at 48% vs Grok 4.1 Fast at 19%.