Command R (03-2024)
Command R (03-2024) places in the top three on AgentDojo.
15
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Cohere Mar 2024 Command R (03-2024)
Open weights Mid-size
No Epoch Capabilities Index score yet
- Vectara Hallucination Leaderboard (HHEM) 4.90% #55 /148
- ThaiExam 37.7% #20 /24
- LegalBench 33% #138 /138
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vectara Hallucination Leaderboard (HHEM) | 4.90% | #55 of 148 | Official leaderboard | |
| WildBench | 35.1 | #30 of 47 | Official leaderboard | |
| MixEval | 77% | #24 of 34 | Official leaderboard | |
| MMLU-Pro | 37.9% | #169 of 212 | Official leaderboard | |
| LMArena (Elo) | 1,227 | #270 of 333 | Official leaderboard | |
| ThaiExam | 37.7% | #20 of 24 | Official leaderboard | |
| EQ-Bench v2 | 56.0 | #73 of 85 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ZebraLogic | 9.90% | #37 of 46 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LegalBench | 33% | #138 of 138 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AgentDojo | 3.34% | #2 of 20 | Official leaderboard | |
| SimpleSafetyTests | 94.3% | #65 of 75 | Official leaderboard | |
| Anthropic Red Team | 93.7% | #70 of 75 | Official leaderboard | |
| HELM Safety | 80.9 | #72 of 75 | Official leaderboard | |
| AIR-Bench 2024 | 31.8% | #80 of 82 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HELM Lite | 29.9 | #59 of 71 | Official leaderboard |