Model comparison
Command A vs Step 2 16k Exp 202412
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 36.5 on the Noometry Index.
Last verified . 12 shared benchmarks.
Cohere
StepFunSummary
- They share 12 benchmarks with published results for both. Command A scores higher in 4 categories and Step 2 16k Exp 202412 in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 2 16k Exp 202412 leads 38.5 to 27.2.
- Command A has downloadable open weights; the other is API-only.
Side by side
| Command A | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | Cohere | StepFun |
| Noometry Index | 36.5 | 39.2 |
| Released | 2025-03-13 | — |
| Weights | Open | Proprietary |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 24 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 2 16k Exp 202412 leads
Command A: 27.2 (#322), Step 2 16k Exp 202412: 38.5 (#174)
| Benchmark | Command A | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1330 | 1316 |
| Aider Polyglot | 12% | — |
Agentic & Tool Use Not comparable
Command A: 35.9 (#40), Step 2 16k Exp 202412: —
| Benchmark | Command A | Step 2 16k Exp 202412 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning Step 2 16k Exp 202412 leads
Command A: 18.3 (#283), Step 2 16k Exp 202412: 25.9 (#142)
| Benchmark | Command A | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1299 |
| Kagi LLM Benchmark | 28.8% | — |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |
Math Too close to call
Command A: 36.2 (#171), Step 2 16k Exp 202412: 36.3 (#169)
| Benchmark | Command A | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1300 | 1304 |
Knowledge Command A leads
Command A: 37.1 (#159), Step 2 16k Exp 202412: 35.2 (#187)
| Benchmark | Command A | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1295 | 1279 |
| Vectara Hallucination Rate | 9.3% | — |
Multilingual Command A leads
Command A: 45.3 (#170), Step 2 16k Exp 202412: 43.7 (#181)
| Benchmark | Command A | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1313 | 1290 |
| LMArena Chinese | 1327 | 1331 |
| LMArena Russian | 1314 | 1324 |
| LMArena French | 1351 | — |
| LMArena German | 1341 | — |
| LMArena Japanese | 1285 | — |
| LMArena Korean | 1285 | — |
| LMArena Spanish | 1347 | — |
Instruction Following Command A leads
Command A: 69.1 (#177), Step 2 16k Exp 202412: 67.9 (#192)
| Benchmark | Command A | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1309 | 1287 |
Long Context Too close to call
Command A: 40.6 (#151), Step 2 16k Exp 202412: 39.7 (#170)
| Benchmark | Command A | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1334 | 1307 |
Writing & Preference Step 2 16k Exp 202412 leads
Command A: 47.6 (#208), Step 2 16k Exp 202412: 52.3 (#173)
| Benchmark | Command A | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1331 | 1321 |
| LMArena Creative Writing | 1319 | 1328 |
| LMArena Multi-Turn | 1339 | 1292 |
| EQ-Bench Creative Writing | 1145 | — |
Frequently asked questions
Is Command A better than Step 2 16k Exp 202412?
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 36.5 on the Noometry Index.
Is Command A or Step 2 16k Exp 202412 better for coding?
Step 2 16k Exp 202412 scores higher on coding benchmarks: 38.5 versus 27.2 in the Noometry coding category.
How many benchmarks do Command A and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Step 2 16k Exp 202412 has 12.