Model comparison
Command R+ vs DeepSeek V4 Pro
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 32.4 on the Noometry Index.
Last verified . 21 shared benchmarks.
Cohere
DeepSeekSummary
- They share 21 benchmarks with published results for both. Command R+ scores higher in 0 categories and DeepSeek V4 Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 9.2.
- The biggest single-benchmark swing is LMCA: 5% for Command R+ and 45.5% for DeepSeek V4 Pro.
- DeepSeek V4 Pro is cheaper at $0.66 / $1.98 per million input/output tokens, against $2.50 / $10 for Command R+.
- DeepSeek V4 Pro accepts more context: 1M tokens versus 128K.
Side by side
| Command R+ | DeepSeek V4 Pro | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 32.4 | 54.3 |
| Released | 2024-08-30 | 2026-04-24 |
| Weights | Open | Open |
| Context window | 128K | 1M |
| Max output | 4K | 393K |
| Input $ / M tokens | $2.50 | $0.66 |
| Output $ / M tokens | $10 | $1.98 |
| Results tracked | 34 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Pro leads
Command R+: 29.1 (#309), DeepSeek V4 Pro: 52.4 (#34)
| Benchmark | Command R+ | DeepSeek V4 Pro |
|---|---|---|
| LMArena Coding | 1187 | 1470 |
| SWE-bench Verified | — | 77.6% |
| FrontierCode | — | 28.6% |
| LMArena WebDev | — | 1582 |
| SciCode | — | 51% |
| WeirdML | — | 66.2% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| ALE-Bench | — | 1,403 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, DeepSeek V4 Pro: 32.8 (#58)
| Benchmark | Command R+ | DeepSeek V4 Pro |
|---|---|---|
| APEX-Agents | — | 47.3% |
| Vending-Bench 2 | — | 3,285 |
Reasoning DeepSeek V4 Pro leads
Command R+: 9.2 (#344), DeepSeek V4 Pro: 56.5 (#24)
| Benchmark | Command R+ | DeepSeek V4 Pro |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1461 |
| DTBench | 54.9% | 93.9% |
| LMCA | 5% | 45.5% |
| Epoch Capabilities Index | 119.34 | 155.31 |
| ARC-AGI-2 | — | 61.3% |
| SimpleBench | 17.4% | — |
| Kagi LLM Benchmark | — | 53.5% |
| NYT Connections (extended) | — | 91.3% |
| ARC-AGI-1 | — | 90.5% |
| CritPt | — | 18% |
| Chess Puzzles | — | 47% |
| LiveBench Reasoning | 24.8% | — |
| Mystery Game Puzzles | — | 43% |
| LiveBench Data Analysis | 38.1% | — |
| Surface Evolver Bench | — | 40% |
| ForecastBench | — | 56.1 |
| LiveBench | 31.8% | — |
Math DeepSeek V4 Pro leads
Command R+: 28.9 (#242), DeepSeek V4 Pro: 64.8 (#30)
| Benchmark | Command R+ | DeepSeek V4 Pro |
|---|---|---|
| LMArena Math | 1188 | 1455 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 26.8% |
| MathArena Final-Answer Competitions | — | 76.6% |
| OTIS Mock AIME 2024-2025 | — | 98.6% |
| ProofBench | — | 50% |
| LiveBench Math | 21.3% | — |
Knowledge DeepSeek V4 Pro leads
Command R+: 36.4 (#169), DeepSeek V4 Pro: 59.5 (#31)
| Benchmark | Command R+ | DeepSeek V4 Pro |
|---|---|---|
| Vectara Hallucination Rate | 6.9% | 8.6% |
| LMArena Expert | 1174 | 1464 |
| GPQA Diamond | — | 91.7% |
| SimpleQA Verified | — | 52.9% |
| MMLU | 69.4% | — |
Multilingual DeepSeek V4 Pro leads
Command R+: 38.6 (#227), DeepSeek V4 Pro: 54.4 (#45)
| Benchmark | Command R+ | DeepSeek V4 Pro |
|---|---|---|
| LMArena Non-English | 1216 | 1439 |
| LMArena Chinese | 1226 | 1486 |
| LMArena French | 1209 | 1472 |
| LMArena German | 1216 | 1458 |
| LMArena Japanese | 1166 | 1445 |
| LMArena Korean | 1138 | 1447 |
| LMArena Russian | 1227 | 1453 |
| LMArena Spanish | 1189 | 1458 |
Instruction Following DeepSeek V4 Pro leads
Command R+: 60.0 (#254), DeepSeek V4 Pro: 76.1 (#47)
| Benchmark | Command R+ | DeepSeek V4 Pro |
|---|---|---|
| LMArena Instruction Following | 1197 | 1448 |
| LiveBench Instruction Following | 57.6% | — |
Long Context DeepSeek V4 Pro leads
Command R+: 37.3 (#219), DeepSeek V4 Pro: 45.0 (#51)
| Benchmark | Command R+ | DeepSeek V4 Pro |
|---|---|---|
| LMArena Longer Query | 1230 | 1458 |
| CL-bench Life | — | 13.5% |
Writing & Preference DeepSeek V4 Pro leads
Command R+: 43.5 (#228), DeepSeek V4 Pro: 65.5 (#46)
| Benchmark | Command R+ | DeepSeek V4 Pro |
|---|---|---|
| LMArena Text | 1229 | 1451 |
| LMArena Creative Writing | 1235 | 1446 |
| LMArena Multi-Turn | 1213 | 1467 |
| EQ-Bench Creative Writing | — | 1553 |
| EQ-Bench 4 | — | 1166 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than DeepSeek V4 Pro?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 32.4 on the Noometry Index.
Which is cheaper, Command R+ or DeepSeek V4 Pro?
DeepSeek V4 Pro is cheaper. It lists at $0.66 per million input tokens and $1.98 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or DeepSeek V4 Pro better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
DeepSeek V4 Pro does, with 1M tokens against 128K.
How many benchmarks do Command R+ and DeepSeek V4 Pro share?
21 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and DeepSeek V4 Pro has 48.