Claude Instant 1.1: benchmark results
Provider: Anthropic. Released 2023-11-22. Access: API.
Unified ELO 1449 ± 1, rank #951 of 1392 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ARC Challenge (AI2) | 85.7 | Accuracy (%) | 86.8 |
| GSM8K | 80.9 | Accuracy (%) | 78.5 |
| ConvRe - Re2Text Hard | 52.3 | Accuracy (%) | 77.8 |
| ConvRe | 57.9 | Average Score (%) | 66.7 |
| ConvRe - Text2Re Easy | 87.2 | Accuracy (%) | 66.7 |
| MMLU | 73.4 | Accuracy (%) | 63.7 |
| TriviaQA | 78.9 | Accuracy (%) | 53.8 |
| ConvRe - Text2Re Hard | 26.2 | Accuracy (%) | 33.3 |
| ConvRe - Re2Text Easy | 65.7 | Accuracy (%) | 11.1 |
Interactive version: theaggregate.ai/model?slug=claude-instant-1-1 · How It Works · Data refreshed daily, snapshot 2026-09-05.