Cohere: AI model benchmarks
AI models from Cohere. 22 models tracked, 22 with a unified ELO rating. Current best: command-a-reasoning-08-2025 (ELO 1609, rank #234 overall). Most recent tracked release: 2026-06-09.
Rated models
| Rank | Model | Provider | Unified ELO | Benchmarks |
|---|---|---|---|---|
| 234 | command-a-reasoning-08-2025 | Cohere | 1609 ± 1 | 16 |
| 359 | North Mini Code | Cohere | 1571 ± 1 | 40 |
| 384 | c4ai-command-a-03-2025 | Cohere | 1564 ± 1 | 31 |
| 423 | Command A+ | Cohere | 1552 ± 1 | 47 |
| 472 | Command A | Cohere | 1541 ± 1 | 347 |
| 480 | c4ai-aya-expanse-32B | Cohere | 1540 ± 1 | 23 |
| 608 | c4ai-aya-expanse-8B | Cohere | 1518 ± 1 | 20 |
| 684 | aya-expanse-32B | Cohere | 1500 ± 1 | 370 |
| 729 | c4ai-command-r-plus | Cohere | 1491 ± 1 | 42 |
| 840 | aya-23-35B | Cohere | 1469 ± 1 | 333 |
| 861 | c4ai-command-r-08-2024 | Cohere | 1466 ± 1 | 88 |
| 903 | Command-R+ | Cohere | 1458 ± 1 | 79 |
| 922 | Command-R+ (08-2024) | Cohere | 1454 ± 1 | 64 |
| 926 | c4ai-command-r-v01 | Cohere | 1453 ± 1 | 63 |
| 951 | c4ai-command-r7B-12-2024 | Cohere | 1448 ± 1 | 51 |
Interactive version: theaggregate.ai/company?slug=cohere · How It Works · Data refreshed daily, snapshot 2026-09-05.