Compare AI models
| Specifications | ||
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 200k | 32k |
| 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. | 30% | — |
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. | 72.7% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 75.4% | — |
| Overview | ||
| Company | Anthropic | |
| Release date | May 22 2025 | Feb 8 2024 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Claude Sonnet 4vsGPT-6.1 SolGemini 1.0 UltravsGPT-6.1 SolClaude Sonnet 4vsMuse Spark OpenGemini 1.0 UltravsMuse Spark OpenClaude Sonnet 4vsGrok 4.7Gemini 1.0 UltravsGrok 4.7Claude Sonnet 4vsDeepSeek-V4.1-Flash-1017Gemini 1.0 UltravsDeepSeek-V4.1-Flash-1017Claude Sonnet 4vsMistral Large 4Gemini 1.0 UltravsMistral Large 4Claude Sonnet 4vsKimi K3Gemini 1.0 UltravsKimi K3Frequently asked questions
Claude Sonnet 4 and Gemini 1.0 Ultra don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Gemini 1.0 Ultra shipped 469 days before Claude Sonnet 4, so benchmark comparisons should account for the intervening progress.
Context windows are 200k (Claude Sonnet 4) vs 32k (Gemini 1.0 Ultra).
Direct benchmark comparisons are unavailable — Claude Sonnet 4 and Gemini 1.0 Ultra don't publish scores on any of the same benchmarks.