Claude 2.1: benchmark results
Anthropic Claude 2.1 legacy chat model. Provider: Anthropic. Released 2023-11-21. Access: API.
Aggregate Rating 1482 ± 11, rank #839 of 1656 rated models, from 149 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| T-Eval | 78.8 | Overall Score (%) | 90 |
| CZ-EVAL - Verbal | 63.36 | Accuracy (%) | 81.8 |
| BenchTable - Utility | 68.8 | Weighted Score (%) | 81.2 |
| HELM Lite - WMT 2014 (cs-en) | 23.09 | BLEU-4 (%) | 77.8 |
| HELM MMLU - Public Relations | 77.27 | EM | 75 |
| CZ-EVAL - Analytical | 38.04 | Accuracy (%) | 72.7 |
| BenchBench | 66.94 | Aggregate Score (%) | 72.1 |
| HELM Lite - LegalBench - Corporate Lobbying | 81.22 | Exact Match (%) | 70 |
| SAD - Facts | 60.08 | Score (%, higher is better) | 70 |
| SAD - Identity Leverage (Situating Prompt) | 54.12 | Score (%, higher is better) | 70 |
| SAD - Self-Recognition | 62.19 | Score (%, higher is better) | 70 |
| HELM MMLU - Global Facts | 55 | EM | 69.2 |
Interactive version: theaggregate.ai/model?slug=claude-2-1 · How It Works · Data refreshed daily, snapshot 2026-10-20.