Claude Instant 1.2: benchmark results
Anthropic Claude Instant 1.2 legacy lower-latency chat model. Provider: Anthropic. Released 2023-08-09. Access: API.
Aggregate Rating 1446 ± 17, rank #1017 of 1656 rated models, from 119 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SAD - Count Tokens | 12.8 | Token-count accuracy (%, higher is better) | 90.9 |
| ARC Challenge (AI2) | 86.3 | Accuracy (%) | 89.5 |
| GSM8K | 86.7 | Accuracy (%) | 88.7 |
| HELM MMLU - Machine Learning | 66.96 | EM | 71.8 |
| SAD - Identity Leverage | 47.99 | Score (%, higher is better) | 70 |
| BenchBench | 64.86 | Aggregate Score (%) | 68.4 |
| SAD - Influence | 64.84 | Score (%, higher is better) | 67.5 |
| SAD - Self-Recognition | 59.81 | Score (%, higher is better) | 65 |
| MMLU | 73.2 | Accuracy (%) | 63.4 |
| AlpacaEval 2.0 | 25.61 | LC Win Rate (%) | 61.7 |
| SAD - Count Tokens (Situating Prompt) | 11.53 | Token-count accuracy (%, higher is better) | 61.4 |
| HELM Lite - WMT 2014 (cs-en) | 21.19 | BLEU-4 (%) | 61.1 |
Interactive version: theaggregate.ai/model?slug=claude-instant-1-2 · How It Works · Data refreshed daily, snapshot 2026-10-20.