Model comparison
Command A vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 36.5 on the Noometry Index.
Last verified . 16 shared benchmarks.
Cohere
StepFunSummary
- They share 16 benchmarks with published results for both. Command A scores higher in 2 categories and Step 3 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 3 leads 40.1 to 27.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 28.8% for Command A and 62.3% for Step 3.
Side by side
| Command A | Step 3 | |
|---|---|---|
| Provider | Cohere | StepFun |
| Noometry Index | 36.5 | 40.5 |
| Released | 2025-03-13 | — |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 24 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Command A: 27.2 (#322), Step 3: 40.1 (#147)
| Benchmark | Command A | Step 3 |
|---|---|---|
| LMArena Coding | 1330 | 1367 |
| Aider Polyglot | 12% | — |
Agentic & Tool Use Not comparable
Command A: 35.9 (#40), Step 3: —
| Benchmark | Command A | Step 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning Step 3 leads
Command A: 18.3 (#283), Step 3: 28.4 (#105)
| Benchmark | Command A | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 62.3% |
| LMArena Hard Prompts | 1326 | 1355 |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |
Math Step 3 leads
Command A: 36.2 (#171), Step 3: 37.6 (#148)
| Benchmark | Command A | Step 3 |
|---|---|---|
| LMArena Math | 1300 | 1366 |
Knowledge Too close to call
Command A: 37.1 (#159), Step 3: 36.8 (#164)
| Benchmark | Command A | Step 3 |
|---|---|---|
| LMArena Expert | 1295 | 1333 |
| Vectara Hallucination Rate | 9.3% | — |
Multimodal Not comparable
Command A: —, Step 3: 35.5 (#86)
| Benchmark | Command A | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Command A: 45.3 (#170), Step 3: 46.3 (#159)
| Benchmark | Command A | Step 3 |
|---|---|---|
| LMArena Non-English | 1313 | 1327 |
| LMArena Chinese | 1327 | 1397 |
| LMArena German | 1341 | 1371 |
| LMArena Korean | 1285 | 1269 |
| LMArena Russian | 1314 | 1331 |
| LMArena Spanish | 1347 | 1371 |
| LMArena French | 1351 | — |
| LMArena Japanese | 1285 | — |
Instruction Following Step 3 leads
Command A: 69.1 (#177), Step 3: 70.4 (#164)
| Benchmark | Command A | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1309 | 1332 |
Long Context Too close to call
Command A: 40.6 (#151), Step 3: 40.3 (#157)
| Benchmark | Command A | Step 3 |
|---|---|---|
| LMArena Longer Query | 1334 | 1326 |
Writing & Preference Step 3 leads
Command A: 47.6 (#208), Step 3: 54.3 (#151)
| Benchmark | Command A | Step 3 |
|---|---|---|
| LMArena Text | 1331 | 1350 |
| LMArena Creative Writing | 1319 | 1321 |
| LMArena Multi-Turn | 1339 | 1341 |
| EQ-Bench Creative Writing | 1145 | — |
Frequently asked questions
Is Command A better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 36.5 on the Noometry Index.
Is Command A or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 27.2 in the Noometry coding category.
How many benchmarks do Command A and Step 3 share?
16 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Step 3 has 17.