Claude Instant 1.2: benchmark results
Anthropic Claude Instant 1.2 legacy lower-latency chat model. Provider: Anthropic. Released 2023-08-09. Access: API.
Unified ELO 1453 ± 1, rank #931 of 1392 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ARC Challenge (AI2) | 86.3 | Accuracy (%) | 89.5 |
| GSM8K | 86.7 | Accuracy (%) | 87.6 |
| BenchBench | 64.86 | Aggregate Score (%) | 68.4 |
| MMLU | 73.2 | Accuracy (%) | 63 |
| AlpacaEval 2.0 | 25.61 | LC Win Rate (%) | 61.7 |
| HELM NaturalQuestions (Open) | 73.1 | F1 (%) | 61.1 |
| HELM WMT 2014 | 19.43 | BLEU-4 (%) | 55.6 |
| TriviaQA | 78.7 | Accuracy (%) | 51.3 |
| HELM Lite | 44.55 | Mean win rate (self-reported) | 43.4 |
| HELM (Stanford) | 39.94 | Mean Win Rate (%) | 37.8 |
| HELM NaturalQuestions (Closed) | 34.32 | F1 (%) | 35 |
| HELM NarrativeQA | 61.59 | F1 (%) | 15.6 |
Interactive version: theaggregate.ai/model?slug=claude-instant-1-2 · How It Works · Data refreshed daily, snapshot 2026-09-05.