Command-R+ (08-2024): benchmark results
August 2024 Command R+ variant, tracked separately from the Command R August 2024 checkpoint. Provider: Cohere. Released 2024-08-21. Access: Open.
Unified ELO 1454 ± 1, rank #925 of 1392 rated models, from 64 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open CoT - LSAT Logical Reasoning | 23.73 | CoT Gain (%) | 99.2 |
| Open LLM Leaderboard - MuSR | 19.84 | Score | 94.6 |
| Open LLM Leaderboard - IFEval | 75.4 | Score | 90.9 |
| Open CoT - LogiQA 2 | 14.76 | CoT Gain (%) | 90.8 |
| Open LLM Leaderboard - GPQA | 13.42 | Score | 87.9 |
| Open CoT Leaderboard | 12.61 | Average CoT Gain (%) | 84.7 |
| Open LLM Leaderboard - BBH | 42.84 | Score | 82 |
| Open LLM Leaderboard - MMLU-Pro | 38.01 | Score | 82 |
| Open CoT - LSAT Reading Comprehension | 18.22 | CoT Gain (%) | 77.5 |
| Vectara Hallucination Leaderboard | 93.1 | Factual Consistency Rate (%) | 72.6 |
| VNTL Leaderboard | 68.53 | Accuracy (%) | 68.6 |
| Enkrypt AI - Jailbreak Risk | 6.71 | Risk Score | 65.5 |
Interactive version: theaggregate.ai/model?slug=command-r-plus-08-2024 · How It Works · Data refreshed daily, snapshot 2026-09-05.