Model comparison
Command R vs DeepSeek-V3.2-Exp
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 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-V3.2-Exp in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.2-Exp leads 62.5 to 38.4.
- The biggest single-benchmark swing is DTBench: 46.4% for Command R and 87.7% for DeepSeek-V3.2-Exp.
- Command R is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.26 / $0.38 for DeepSeek-V3.2-Exp.
- DeepSeek-V3.2-Exp accepts more context: 164K tokens versus 128K.
Side by side
| Command R | DeepSeek-V3.2-Exp | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 31.0 | 44.9 |
| Released | 2024-08-30 | 2025-09-29 |
| Weights | Open | Open |
| Context window | 128K | 164K |
| Max output | 4K | 66K |
| Input $ / M tokens | $0.15 | $0.26 |
| Output $ / M tokens | $0.60 | $0.38 |
| Results tracked | 29 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.2-Exp leads
Command R: 28.8 (#301), DeepSeek-V3.2-Exp: 46.4 (#61)
| Benchmark | Command R | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Coding | 1170 | 1454 |
| SWE-bench Verified (bash only) | — | 70% |
| Aider Polyglot | — | 74.2% |
| LMArena WebDev | — | 1362 |
| SWE-bench Multilingual | — | 59% |
| SciCode | — | 38.9% |
| WeirdML | — | 39.5% |
| BigCodeBench Instruct | 37.1% | — |
| LiveBench Coding | 17.9% | — |
| BigCodeBench Complete | 45.2% | — |
Agentic & Tool Use Not comparable
Command R: —, DeepSeek-V3.2-Exp: 37.9 (#31)
| Benchmark | Command R | DeepSeek-V3.2-Exp |
|---|---|---|
| Terminal-Bench | — | 39.6% |
| Berkeley Function Calling Leaderboard | — | 56.7% |
| TheAgentCompany | — | 42.9% |
| Vending-Bench 2 | — | 1,034 |
Reasoning DeepSeek-V3.2-Exp leads
Command R: 13.3 (#329), DeepSeek-V3.2-Exp: 22.0 (#185)
| Benchmark | Command R | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1433 |
| DTBench | 46.4% | 87.7% |
| LMCA | 9.2% | 29.1% |
| ARC-AGI-2 | — | 4% |
| Kagi LLM Benchmark | — | 52.2% |
| NYT Connections (extended) | — | 36.7% |
| ARC-AGI-1 | — | 57% |
| CritPt | — | 2.9% |
| Chess Puzzles | — | 14% |
| Thematic Generalization | — | 65% |
| LiveBench Reasoning | 21.9% | — |
| LiveBench Data Analysis | 33.3% | — |
| Epoch Capabilities Index | — | 146.28 |
| LiveBench | 27.5% | — |
Math DeepSeek-V3.2-Exp leads
Command R: 25.8 (#244), DeepSeek-V3.2-Exp: 40.8 (#75)
| Benchmark | Command R | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Math | 1155 | 1435 |
| MathArena Final-Answer Competitions | — | 57.7% |
| OTIS Mock AIME 2024-2025 | — | 87.8% |
| ProofBench | — | 8% |
| LiveBench Math | 19.4% | — |
| FrontierMath (Feb 2025 set) | — | 22.1% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge DeepSeek-V3.2-Exp leads
Command R: 30.5 (#219), DeepSeek-V3.2-Exp: 51.6 (#61)
| Benchmark | Command R | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Expert | 1138 | 1436 |
| GPQA Diamond | — | 83.4% |
| Vectara Hallucination Rate | — | 5.3% |
| MMLU | 65.2% | — |
Multilingual DeepSeek-V3.2-Exp leads
Command R: 35.9 (#240), DeepSeek-V3.2-Exp: 52.4 (#85)
| Benchmark | Command R | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Non-English | 1174 | 1409 |
| LMArena Chinese | 1182 | 1461 |
| LMArena French | 1161 | 1435 |
| LMArena German | 1176 | 1440 |
| LMArena Japanese | 1143 | 1377 |
| LMArena Korean | 1162 | 1372 |
| LMArena Russian | 1174 | 1423 |
| LMArena Spanish | 1150 | 1441 |
Instruction Following DeepSeek-V3.2-Exp leads
Command R: 58.3 (#256), DeepSeek-V3.2-Exp: 74.7 (#89)
| Benchmark | Command R | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Instruction Following | 1167 | 1413 |
| LiveBench Instruction Following | 55.6% | — |
Long Context DeepSeek-V3.2-Exp leads
Command R: 36.3 (#226), DeepSeek-V3.2-Exp: 47.6 (#15)
| Benchmark | Command R | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Longer Query | 1198 | 1428 |
| Fiction.LiveBench | — | 83.3% |
| CL-bench | — | 13.2% |
| CL-bench Life | — | 9.5% |
Writing & Preference DeepSeek-V3.2-Exp leads
Command R: 38.4 (#248), DeepSeek-V3.2-Exp: 62.5 (#73)
| Benchmark | Command R | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Text | 1187 | 1425 |
| LMArena Creative Writing | 1170 | 1403 |
| LMArena Multi-Turn | 1163 | 1427 |
| EQ-Bench Creative Writing | — | 1515 |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than DeepSeek-V3.2-Exp?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 31.0 on the Noometry Index.
Which is cheaper, Command R or DeepSeek-V3.2-Exp?
Command R is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; DeepSeek-V3.2-Exp lists at $0.26 and $0.38.
Is Command R or DeepSeek-V3.2-Exp better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.4 versus 28.8 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.2-Exp does, with 164K tokens against 128K.
How many benchmarks do Command R and DeepSeek-V3.2-Exp share?
19 benchmarks have published results for both models. Command R has 29 scored results on Noometry and DeepSeek-V3.2-Exp has 48.