Model comparison
Command A vs Granite 4.2 3b
Granite 4.2 3b is the stronger model overall, scoring 39.0 to 35.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
CohereSummary
- They share 11 benchmarks with published results for both. Command A scores higher in 4 categories and Granite 4.2 3b in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where Granite 4.2 3b leads 39.4 to 26.8.
Side by side
| Command A | Granite 4.2 3b | |
|---|---|---|
| Provider | Cohere | IBM |
| Noometry Index | 35.9 | 39.0 |
| 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 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.2 3b leads
Command A: 26.8 (#317), Granite 4.2 3b: 39.4 (#146)
| Benchmark | Command A | Granite 4.2 3b |
|---|---|---|
| LMArena Coding | 1331 | 1363 |
| Aider Polyglot | 12% | — |
Agentic & Tool Use Not comparable
Command A: 35.7 (#36), Granite 4.2 3b: —
| Benchmark | Command A | Granite 4.2 3b |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning Granite 4.2 3b leads
Command A: 17.7 (#276), Granite 4.2 3b: 25.0 (#136)
| Benchmark | Command A | Granite 4.2 3b |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1308 |
| Kagi LLM Benchmark | 28.8% | — |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |
Math Not comparable
Command A: 33.5 (#172), Granite 4.2 3b: —
| Benchmark | Command A | Granite 4.2 3b |
|---|---|---|
| LMArena Math | 1300 | — |
Knowledge Too close to call
Command A: 36.5 (#157), Granite 4.2 3b: 35.6 (#169)
| Benchmark | Command A | Granite 4.2 3b |
|---|---|---|
| LMArena Expert | 1295 | 1313 |
| Vectara Hallucination Rate | 9.3% | — |
Multilingual Command A leads
Command A: 45.5 (#166), Granite 4.2 3b: 42.4 (#193)
| Benchmark | Command A | Granite 4.2 3b |
|---|---|---|
| LMArena Non-English | 1313 | 1268 |
| LMArena Chinese | 1327 | 1268 |
| LMArena Russian | 1314 | 1249 |
| LMArena French | 1352 | — |
| LMArena German | 1341 | — |
| LMArena Japanese | 1283 | — |
| LMArena Korean | 1285 | — |
| LMArena Spanish | 1346 | — |
Instruction Following Command A leads
Command A: 69.3 (#172), Granite 4.2 3b: 67.2 (#195)
| Benchmark | Command A | Granite 4.2 3b |
|---|---|---|
| LMArena Instruction Following | 1309 | 1271 |
Long Context Command A leads
Command A: 40.6 (#147), Granite 4.2 3b: 39.3 (#179)
| Benchmark | Command A | Granite 4.2 3b |
|---|---|---|
| LMArena Longer Query | 1334 | 1293 |
Writing & Preference Too close to call
Command A: 47.8 (#204), Granite 4.2 3b: 47.9 (#202)
| Benchmark | Command A | Granite 4.2 3b |
|---|---|---|
| LMArena Text | 1331 | 1295 |
| LMArena Creative Writing | 1319 | 1215 |
| LMArena Multi-Turn | 1338 | 1293 |
| EQ-Bench Creative Writing | 1145 | — |
Frequently asked questions
Is Command A better than Granite 4.2 3b?
Granite 4.2 3b is the stronger model overall, scoring 39.0 to 35.9 on the Noometry Index.
Is Command A or Granite 4.2 3b better for coding?
Granite 4.2 3b scores higher on coding benchmarks: 39.4 versus 26.8 in the Noometry coding category.
How many benchmarks do Command A and Granite 4.2 3b share?
11 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Granite 4.2 3b has 11.