Model comparison
Command R vs Mercury
Mercury is the stronger model overall, scoring 37.6 to 31.4 on the Noometry Index.
Last verified . 8 shared benchmarks.
CohereSummary
- They share 8 benchmarks with published results for both. Command R scores higher in 0 categories and Mercury in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where Mercury leads 38.7 to 29.3.
- Command R has downloadable open weights; the other is API-only.
Side by side
| Command R | Mercury | |
|---|---|---|
| Provider | Cohere | Inception |
| Noometry Index | 31.4 | 37.6 |
| Released | 2024-08-30 | — |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 29 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury leads
Command R: 29.3 (#306), Mercury: 38.7 (#170)
| Benchmark | Command R | Mercury |
|---|---|---|
| LMArena Coding | 1169 | 1322 |
| BigCodeBench Instruct | 37.1% | — |
| LiveBench Coding | 17.9% | — |
| BigCodeBench Complete | 45.2% | — |
Reasoning Mercury leads
Command R: 13.8 (#331), Mercury: 17.5 (#293)
| Benchmark | Command R | Mercury |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1285 |
| Kagi LLM Benchmark | — | 21.6% |
| LiveBench Reasoning | 21.9% | — |
| DTBench | 46.4% | — |
| LiveBench Data Analysis | 33.3% | — |
| LMCA | 9.2% | — |
| LiveBench | 27.5% | — |
Math Not comparable
Command R: 28.0 (#246), Mercury: —
| Benchmark | Command R | Mercury |
|---|---|---|
| LiveBench Math | 19.4% | — |
| LMArena Math | 1155 | — |
Knowledge Not comparable
Command R: 31.0 (#221), Mercury: —
| Benchmark | Command R | Mercury |
|---|---|---|
| LMArena Expert | 1138 | — |
| MMLU | 65.2% | — |
Multilingual Mercury leads
Command R: 35.7 (#245), Mercury: 41.6 (#206)
| Benchmark | Command R | Mercury |
|---|---|---|
| LMArena Non-English | 1174 | 1260 |
| LMArena Chinese | 1182 | — |
| LMArena French | 1162 | — |
| LMArena German | 1176 | — |
| LMArena Japanese | 1143 | — |
| LMArena Korean | 1163 | — |
| LMArena Russian | 1174 | — |
| LMArena Spanish | 1151 | — |
Instruction Following Mercury leads
Command R: 58.1 (#261), Mercury: 65.2 (#224)
| Benchmark | Command R | Mercury |
|---|---|---|
| LMArena Instruction Following | 1167 | 1239 |
| LiveBench Instruction Following | 55.6% | — |
Long Context Mercury leads
Command R: 36.3 (#231), Mercury: 38.4 (#198)
| Benchmark | Command R | Mercury |
|---|---|---|
| LMArena Longer Query | 1198 | 1266 |
Writing & Preference Mercury leads
Command R: 38.2 (#254), Mercury: 46.2 (#221)
| Benchmark | Command R | Mercury |
|---|---|---|
| LMArena Text | 1187 | 1282 |
| LMArena Creative Writing | 1170 | 1191 |
| LMArena Multi-Turn | 1163 | 1282 |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than Mercury?
Mercury is the stronger model overall, scoring 37.6 to 31.4 on the Noometry Index.
Is Command R or Mercury better for coding?
Mercury scores higher on coding benchmarks: 38.7 versus 29.3 in the Noometry coding category.
How many benchmarks do Command R and Mercury share?
8 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Mercury has 9.