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. | 100k | 2M |
| These models have no shared benchmark scores. | ||
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | 58.7% | — |
GSM8KGrade-school math — Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | 86.7% | — |
| Overview | ||
| Company | Anthropic | |
| Release date | Aug 9 2023 | Sep 24 2024 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Claude Instant 1.2vsGPT-6.1 SolGemini 1.5 Pro-002vsGPT-6.1 SolClaude Instant 1.2vsMuse Spark OpenGemini 1.5 Pro-002vsMuse Spark OpenClaude Instant 1.2vsGrok 4.7Gemini 1.5 Pro-002vsGrok 4.7Claude Instant 1.2vsDeepSeek-V4.1-Flash-1017Gemini 1.5 Pro-002vsDeepSeek-V4.1-Flash-1017Claude Instant 1.2vsMistral Large 4Gemini 1.5 Pro-002vsMistral Large 4Claude Instant 1.2vsKimi K3Gemini 1.5 Pro-002vsKimi K3Frequently asked questions
Claude Instant 1.2 and Gemini 1.5 Pro-002 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Claude Instant 1.2 shipped 412 days before Gemini 1.5 Pro-002, so benchmark comparisons should account for the intervening progress.
Context windows are 100k (Claude Instant 1.2) vs 2M (Gemini 1.5 Pro-002).
Direct benchmark comparisons are unavailable — Claude Instant 1.2 and Gemini 1.5 Pro-002 don't publish scores on any of the same benchmarks.