Model comparison
Command A vs Palm 2
Command A is the stronger model overall, scoring 36.5 to 30.0 on the Noometry Index.
Last verified . 10 shared benchmarks.
Cohere
GoogleSummary
- They share 10 benchmarks with published results for both. Command A scores higher in 5 categories and Palm 2 in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Command A leads 45.3 to 20.9.
- Command A has downloadable open weights; the other is API-only.
Side by side
| Command A | Palm 2 | |
|---|---|---|
| Provider | Cohere | |
| Noometry Index | 36.5 | 30.0 |
| 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 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Palm 2 leads
Command A: 27.2 (#322), Palm 2: 29.0 (#311)
| Benchmark | Command A | Palm 2 |
|---|---|---|
| LMArena Coding | 1330 | 994 |
| Aider Polyglot | 12% | — |
Agentic & Tool Use Not comparable
Command A: 35.9 (#40), Palm 2: —
| Benchmark | Command A | Palm 2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning Too close to call
Command A: 18.3 (#283), Palm 2: 19.1 (#271)
| Benchmark | Command A | Palm 2 |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1005 |
| Kagi LLM Benchmark | 28.8% | — |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |
Math Command A leads
Command A: 36.2 (#171), Palm 2: 30.8 (#231)
| Benchmark | Command A | Palm 2 |
|---|---|---|
| LMArena Math | 1300 | 1049 |
Knowledge Not comparable
Command A: 37.1 (#159), Palm 2: —
| Benchmark | Command A | Palm 2 |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | — |
| LMArena Expert | 1295 | — |
Multilingual Command A leads
Command A: 45.3 (#170), Palm 2: 20.9 (#295)
| Benchmark | Command A | Palm 2 |
|---|---|---|
| LMArena Non-English | 1313 | 916 |
| LMArena Chinese | 1327 | 887 |
| LMArena French | 1351 | — |
| LMArena German | 1341 | — |
| LMArena Japanese | 1285 | — |
| LMArena Korean | 1285 | — |
| LMArena Russian | 1314 | — |
| LMArena Spanish | 1347 | — |
Instruction Following Command A leads
Command A: 69.1 (#177), Palm 2: 51.0 (#296)
| Benchmark | Command A | Palm 2 |
|---|---|---|
| LMArena Instruction Following | 1309 | 1010 |
Long Context Command A leads
Command A: 40.6 (#151), Palm 2: 30.8 (#285)
| Benchmark | Command A | Palm 2 |
|---|---|---|
| LMArena Longer Query | 1334 | 1010 |
Writing & Preference Command A leads
Command A: 47.6 (#208), Palm 2: 25.6 (#304)
| Benchmark | Command A | Palm 2 |
|---|---|---|
| LMArena Text | 1331 | 1027 |
| LMArena Creative Writing | 1319 | 991 |
| LMArena Multi-Turn | 1339 | 994 |
| EQ-Bench Creative Writing | 1145 | — |
Frequently asked questions
Is Command A better than Palm 2?
Command A is the stronger model overall, scoring 36.5 to 30.0 on the Noometry Index.
Is Command A or Palm 2 better for coding?
Palm 2 scores higher on coding benchmarks: 29.0 versus 27.2 in the Noometry coding category.
How many benchmarks do Command A and Palm 2 share?
10 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Palm 2 has 10.