Model comparison
Command R vs DeepSeek-V2.5 (Sep 2024)
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.0 to 31.0 on the Noometry Index.
Last verified . 19 shared benchmarks.
Cohere
DeepSeekSummary
- They share 19 benchmarks with published results for both. Command R scores higher in 0 categories and DeepSeek-V2.5 (Sep 2024) in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V2.5 (Sep 2024) leads 50.0 to 38.4.
- The biggest single-benchmark swing is BigCodeBench Instruct: 37.1% for Command R and 48.6% for DeepSeek-V2.5 (Sep 2024).
Side by side
| Command R | DeepSeek-V2.5 (Sep 2024) | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 31.0 | 37.0 |
| Released | 2024-08-30 | 2024-09-06 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 29 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2.5 (Sep 2024) leads
Command R: 28.8 (#301), DeepSeek-V2.5 (Sep 2024): 31.3 (#274)
| Benchmark | Command R | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| BigCodeBench Instruct | 37.1% | 48.6% |
| LMArena Coding | 1170 | 1310 |
| BigCodeBench Complete | 45.2% | 53.2% |
| Aider Polyglot | — | 17.8% |
| LiveBench Coding | 17.9% | — |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 74.1% |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
Command R: 13.3 (#329), DeepSeek-V2.5 (Sep 2024): 24.5 (#145)
| Benchmark | Command R | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1289 |
| LiveBench Reasoning | 21.9% | — |
| DTBench | 46.4% | — |
| LiveBench Data Analysis | 33.3% | — |
| LMCA | 9.2% | — |
| LiveBench | 27.5% | — |
Math DeepSeek-V2.5 (Sep 2024) leads
Command R: 25.8 (#244), DeepSeek-V2.5 (Sep 2024): 33.3 (#177)
| Benchmark | Command R | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Math | 1155 | 1289 |
| LiveBench Math | 19.4% | — |
Knowledge DeepSeek-V2.5 (Sep 2024) leads
Command R: 30.5 (#219), DeepSeek-V2.5 (Sep 2024): 34.2 (#190)
| Benchmark | Command R | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Expert | 1138 | 1266 |
| MMLU | 65.2% | — |
Multilingual DeepSeek-V2.5 (Sep 2024) leads
Command R: 35.9 (#240), DeepSeek-V2.5 (Sep 2024): 42.7 (#188)
| Benchmark | Command R | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Non-English | 1174 | 1273 |
| LMArena Chinese | 1182 | 1317 |
| LMArena French | 1161 | 1288 |
| LMArena German | 1176 | 1258 |
| LMArena Japanese | 1143 | 1228 |
| LMArena Korean | 1162 | 1209 |
| LMArena Russian | 1174 | 1289 |
| LMArena Spanish | 1150 | 1248 |
Instruction Following DeepSeek-V2.5 (Sep 2024) leads
Command R: 58.3 (#256), DeepSeek-V2.5 (Sep 2024): 67.7 (#189)
| Benchmark | Command R | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Instruction Following | 1167 | 1280 |
| LiveBench Instruction Following | 55.6% | — |
Long Context DeepSeek-V2.5 (Sep 2024) leads
Command R: 36.3 (#226), DeepSeek-V2.5 (Sep 2024): 39.5 (#169)
| Benchmark | Command R | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Longer Query | 1198 | 1301 |
Writing & Preference DeepSeek-V2.5 (Sep 2024) leads
Command R: 38.4 (#248), DeepSeek-V2.5 (Sep 2024): 50.0 (#182)
| Benchmark | Command R | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Text | 1187 | 1294 |
| LMArena Creative Writing | 1170 | 1285 |
| LMArena Multi-Turn | 1163 | 1297 |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than DeepSeek-V2.5 (Sep 2024)?
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.0 to 31.0 on the Noometry Index.
Is Command R or DeepSeek-V2.5 (Sep 2024) better for coding?
DeepSeek-V2.5 (Sep 2024) scores higher on coding benchmarks: 31.3 versus 28.8 in the Noometry coding category.
How many benchmarks do Command R and DeepSeek-V2.5 (Sep 2024) share?
19 benchmarks have published results for both models. Command R has 29 scored results on Noometry and DeepSeek-V2.5 (Sep 2024) has 22.