Command R (08-2024)
Command / Cohere
25scores
18benchmarks
$2.5 / $10 per 1M tokenscost in/out
Metadata
Command Closed/API
Aliases: cohere-command-r-plus-08-2024, cohere/command-r-plus-08-2024, command-r-plus-08-2024
| Benchmark | Category | Rank | Score | Sampled |
|---|---|---|---|---|
| BigCodeBench | Coding | 94 | 33.80 | 2026-05-06 |
| SciCode | Coding | 415 | 11.8% | 2026-05-11 |
| SciCode | Coding | 446 | 6.2% | 2026-05-11 |
| MixEval Chat | General Knowledge | 19 | 51.40 | 2026-05-06 |
| MixEval Chat | General Knowledge | 28 | 45.20 | 2026-05-06 |
| HELM AIR-Bench | Generalization | 85 | 0.317966 | 2026-05-28 |
| HELM Safety | Generalization | 59 | 0.809403 | 2026-05-28 |
| WildBench | Generalization | 40 | 6.7529296875 | 2026-05-27 |
| Artificial Analysis Intelligence Index | Intelligence | 464 | 8.35 | 2026-05-11 |
| Artificial Analysis Intelligence Index | Intelligence | 484 | 7.41 | 2026-05-11 |
| HELM Lite | Intelligence | 58 | 0.333650 | 2026-05-28 |
| Humanity's Last Exam | Intelligence | 323 | 4.8% | 2026-05-11 |
| Humanity's Last Exam | Intelligence | 356 | 4.5% | 2026-05-11 |
| MMLU-Pro | Intelligence | 310 | 43.2% | 2026-05-11 |
| MMLU-Pro | Intelligence | 330 | 33.8% | 2026-05-11 |
| LegalBench | Legal | 111 | 32.965% | 2026-05-28 |
| BenchBench | Meta | 97 | 0.33 | 2026-05-06 |
| GPQA Diamond | Reasoning | 434 | 32.3% | 2026-05-11 |
| GPQA Diamond | Reasoning | 457 | 28.4% | 2026-05-11 |
| ZebraLogic | Reasoning | 57 | 9.90 | 2026-05-06 |
| ChemBench | Science | 40 | 0.45 | 2026-05-06 |
| IDE-Bench | Software Engineering | 15 | 0 | 2026-05-27 |
| VNTL Leaderboard | Translation | 22 | 68.53 | 2026-05-06 |
| VNTL Leaderboard | Translation | 39 | 65.20 | 2026-05-06 |
| TruthfulQA | Truthfulness | 11 | 0.56 | 2026-05-06 |
No matching rows.