Claude 1vsClaude Instant 1.2
Claude 1 | Claude Instant 1.2 | |
|---|---|---|
| Specifications | ||
Context window | 9k | 100k |
| Benchmarks | ||
Function synthesis HumanEval164 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% |
Grade-school math GSM8KGrade-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 | Anthropic |
| Release date | Mar 14 2023 | Aug 9 2023 |
| Access | Proprietary | Proprietary |
Which is better: Claude 1 or Claude Instant 1.2?
Claude 1 and Claude Instant 1.2 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Claude 1 shipped 148 days before Claude Instant 1.2, so benchmark comparisons should account for the intervening progress.
Context windows are 9k (Claude 1) vs 100k (Claude Instant 1.2).
Direct benchmark comparisons are unavailable — Claude 1 and Claude Instant 1.2 don't publish scores on any of the same benchmarks.
Frequently asked questions
Claude 1 was released by Anthropic on Mar 14 2023.
Claude Instant 1.2 was released by Anthropic on Aug 9 2023.
Claude 1 has a 9k context window; Claude Instant 1.2 has 100k.
Other comparisons
Claude 1vsGPT-5.6 SolClaude Instant 1.2vsGPT-5.6 SolClaude 1vsGemini 3.6 FlashClaude Instant 1.2vsGemini 3.6 FlashClaude 1vsMuse GlimmerClaude Instant 1.2vsMuse GlimmerClaude 1vsGrok 4.5Claude Instant 1.2vsGrok 4.5Claude 1vsDeepSeek-V4-Flash-0731Claude Instant 1.2vsDeepSeek-V4-Flash-0731Claude 1vsMistral Medium 3.5Claude Instant 1.2vsMistral Medium 3.5