Model comparison
Command A vs DeepSeek V4 Flash
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 35.9 on the Noometry Index.
Last verified . 21 shared benchmarks.
Cohere
DeepSeekSummary
- They share 21 benchmarks with published results for both. Command A scores higher in 0 categories and DeepSeek V4 Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 17.7.
- The biggest single-benchmark swing is LMCA: 10.3% for Command A and 41.7% for DeepSeek V4 Flash.
- DeepSeek V4 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $2.50 / $10 for Command A.
- DeepSeek V4 Flash accepts more context: 1M tokens versus 256K.
Side by side
| Command A | DeepSeek V4 Flash | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 35.9 | 53.6 |
| Released | 2025-03-13 | 2026-04-24 |
| Weights | Open | Open |
| Context window | 256K | 1M |
| Max output | 8K | 393K |
| Input $ / M tokens | $2.50 | $0.15 |
| Output $ / M tokens | $10 | $0.60 |
| Results tracked | 24 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Flash leads
Command A: 26.8 (#317), DeepSeek V4 Flash: 47.6 (#56)
| Benchmark | Command A | DeepSeek V4 Flash |
|---|---|---|
| LMArena Coding | 1331 | 1457 |
| FrontierCode | — | 18.8% |
| Aider Polyglot | 12% | — |
| LMArena WebDev | — | 1581 |
| SciCode | — | 49.9% |
| WeirdML | — | 63% |
| ALE-Bench | — | 1,306 |
Agentic & Tool Use Not comparable
Command A: 35.7 (#36), DeepSeek V4 Flash: —
| Benchmark | Command A | DeepSeek V4 Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning DeepSeek V4 Flash leads
Command A: 17.7 (#276), DeepSeek V4 Flash: 53.7 (#25)
| Benchmark | Command A | DeepSeek V4 Flash |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 52.2% |
| LMArena Hard Prompts | 1326 | 1443 |
| DTBench | 61.3% | 90.9% |
| LMCA | 10.3% | 41.7% |
| ARC-AGI-2 | — | 61.4% |
| SimpleBench | — | 61.1% |
| NYT Connections (extended) | — | 89.6% |
| ARC-AGI-1 | — | 89% |
| CritPt | — | 16.6% |
| Chess Puzzles | — | 33% |
| Mystery Game Puzzles | — | 34% |
| Epoch Capabilities Index | — | 154.51 |
Math DeepSeek V4 Flash leads
Command A: 33.5 (#172), DeepSeek V4 Flash: 60.0 (#31)
| Benchmark | Command A | DeepSeek V4 Flash |
|---|---|---|
| LMArena Math | 1300 | 1427 |
| FrontierMath (Tiers 1-3) | — | 57.5% |
| FrontierMath Tier 4 | — | 24.4% |
| MathArena Final-Answer Competitions | — | 76.5% |
| OTIS Mock AIME 2024-2025 | — | 94.4% |
| ProofBench | — | 56% |
Knowledge DeepSeek V4 Flash leads
Command A: 36.5 (#157), DeepSeek V4 Flash: 55.5 (#43)
| Benchmark | Command A | DeepSeek V4 Flash |
|---|---|---|
| LMArena Expert | 1295 | 1441 |
| GPQA Diamond | — | 91% |
| SimpleQA Verified | — | 33.6% |
| Vectara Hallucination Rate | 9.3% | — |
Multilingual DeepSeek V4 Flash leads
Command A: 45.5 (#166), DeepSeek V4 Flash: 53.2 (#71)
| Benchmark | Command A | DeepSeek V4 Flash |
|---|---|---|
| LMArena Non-English | 1313 | 1420 |
| LMArena Chinese | 1327 | 1467 |
| LMArena French | 1352 | 1438 |
| LMArena German | 1341 | 1418 |
| LMArena Japanese | 1283 | 1403 |
| LMArena Korean | 1285 | 1383 |
| LMArena Russian | 1314 | 1428 |
| LMArena Spanish | 1346 | 1437 |
Instruction Following DeepSeek V4 Flash leads
Command A: 69.3 (#172), DeepSeek V4 Flash: 75.1 (#76)
| Benchmark | Command A | DeepSeek V4 Flash |
|---|---|---|
| LMArena Instruction Following | 1309 | 1421 |
Long Context DeepSeek V4 Flash leads
Command A: 40.6 (#147), DeepSeek V4 Flash: 43.8 (#81)
| Benchmark | Command A | DeepSeek V4 Flash |
|---|---|---|
| LMArena Longer Query | 1334 | 1435 |
Writing & Preference DeepSeek V4 Flash leads
Command A: 47.8 (#204), DeepSeek V4 Flash: 64.0 (#59)
| Benchmark | Command A | DeepSeek V4 Flash |
|---|---|---|
| LMArena Text | 1331 | 1432 |
| LMArena Creative Writing | 1319 | 1403 |
| EQ-Bench Creative Writing | 1145 | 1559 |
| LMArena Multi-Turn | 1338 | 1449 |
Frequently asked questions
Is Command A better than DeepSeek V4 Flash?
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 35.9 on the Noometry Index.
Which is cheaper, Command A or DeepSeek V4 Flash?
DeepSeek V4 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or DeepSeek V4 Flash better for coding?
DeepSeek V4 Flash scores higher on coding benchmarks: 47.6 versus 26.8 in the Noometry coding category.
Which has the bigger context window?
DeepSeek V4 Flash does, with 1M tokens against 256K.
How many benchmarks do Command A and DeepSeek V4 Flash share?
21 benchmarks have published results for both models. Command A has 24 scored results on Noometry and DeepSeek V4 Flash has 41.