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. | 10% | 15% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 33.3% | — |
| Overview | ||
| Company | Anthropic | |
| Release date | Mar 4 2024 | Jan 30 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Claude 3 HaikuvsGPT-6.1 SolGemini 2.0 FlashvsGPT-6.1 SolClaude 3 HaikuvsMuse WonderGemini 2.0 FlashvsMuse WonderClaude 3 HaikuvsGrok 4.7Gemini 2.0 FlashvsGrok 4.7Claude 3 HaikuvsDeepSeek-V4.1-FlashGemini 2.0 FlashvsDeepSeek-V4.1-FlashClaude 3 HaikuvsMistral Large 4Gemini 2.0 FlashvsMistral Large 4Claude 3 HaikuvsKimi K3Gemini 2.0 FlashvsKimi K3Frequently asked questions
Gemini 2.0 Flash leads Claude 3 Haiku on 1 of the 1 benchmark they both report (BullshitBench v2). Claude 3 Haiku shipped 332 days before Gemini 2.0 Flash, 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 2.0 Flash leads at 15% vs Claude 3 Haiku at 10%.