Model comparison
Command A vs Gemma 3 27B
Command A is the stronger model overall, scoring 36.5 to 30.8 on the Noometry Index. Gemma 3 27B costs 44× less per token, which makes it the better buy when Command A's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
Cohere
GoogleSummary
- They share 24 benchmarks with published results for both. Command A scores higher in 6 categories and Gemma 3 27B in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where Command A leads 40.6 to 27.6.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 57.1% for Command A and 29.5% for Gemma 3 27B.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $2.50 / $10 for Command A.
- Command A accepts more context: 256K tokens versus 131K.
Side by side
| Command A | Gemma 3 27B | |
|---|---|---|
| Provider | Cohere | |
| Noometry Index | 36.5 | 30.8 |
| Released | 2025-03-13 | 2025-03-11 |
| Weights | Open | Open |
| Context window | 256K | 131K |
| Max output | 8K | 8K |
| Input $ / M tokens | $2.50 | $0.08 |
| Output $ / M tokens | $10 | $0.16 |
| Results tracked | 24 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Command A leads
Command A: 27.2 (#322), Gemma 3 27B: 22.5 (#334)
| Benchmark | Command A | Gemma 3 27B |
|---|---|---|
| Aider Polyglot | 12% | 4.9% |
| LMArena Coding | 1330 | 1322 |
| SciCode | — | 21.2% |
| LiveBench Coding | — | 39.9% |
Agentic & Tool Use Command A leads
Command A: 35.9 (#40), Gemma 3 27B: 25.1 (#110)
| Benchmark | Command A | Gemma 3 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | 29.5% |
Reasoning Command A leads
Command A: 18.3 (#283), Gemma 3 27B: 16.7 (#301)
| Benchmark | Command A | Gemma 3 27B |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 40.4% |
| LMArena Hard Prompts | 1326 | 1340 |
| DTBench | 61.3% | 52.5% |
| LMCA | 10.3% | 12.3% |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 43.8% |
| LiveBench Data Analysis | — | 51.5% |
| Epoch Capabilities Index | — | 130.04 |
| LiveBench | — | 50% |
Math Command A leads
Command A: 36.2 (#171), Gemma 3 27B: 25.9 (#265)
| Benchmark | Command A | Gemma 3 27B |
|---|---|---|
| LMArena Math | 1300 | 1312 |
| OTIS Mock AIME 2024-2025 | — | 22.5% |
| LiveBench Math | — | 55.4% |
| MATH Level 5 | — | 74% |
Knowledge Command A leads
Command A: 37.1 (#159), Gemma 3 27B: 25.5 (#261)
| Benchmark | Command A | Gemma 3 27B |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 7.4% |
| LMArena Expert | 1295 | 1304 |
| GPQA Diamond | — | 47.7% |
| Confabulations | — | 40.3% |
Multimodal Not comparable
Command A: —, Gemma 3 27B: 32.6 (#100)
| Benchmark | Command A | Gemma 3 27B |
|---|---|---|
| LMArena Vision | — | 1164 |
| GeoBench | — | 52% |
Multilingual Gemma 3 27B leads
Command A: 45.3 (#170), Gemma 3 27B: 46.9 (#155)
| Benchmark | Command A | Gemma 3 27B |
|---|---|---|
| LMArena Non-English | 1313 | 1334 |
| LMArena Chinese | 1327 | 1346 |
| LMArena French | 1351 | 1368 |
| LMArena German | 1341 | 1362 |
| LMArena Japanese | 1285 | 1287 |
| LMArena Korean | 1285 | 1308 |
| LMArena Russian | 1314 | 1349 |
| LMArena Spanish | 1347 | 1349 |
Instruction Following Gemma 3 27B leads
Command A: 69.1 (#177), Gemma 3 27B: 70.6 (#160)
| Benchmark | Command A | Gemma 3 27B |
|---|---|---|
| LMArena Instruction Following | 1309 | 1321 |
| LiveBench Instruction Following | — | 74.9% |
Long Context Command A leads
Command A: 40.6 (#151), Gemma 3 27B: 27.6 (#293)
| Benchmark | Command A | Gemma 3 27B |
|---|---|---|
| LMArena Longer Query | 1334 | 1333 |
| Fiction.LiveBench | — | 33.3% |
Writing & Preference Gemma 3 27B leads
Command A: 47.6 (#208), Gemma 3 27B: 52.5 (#168)
| Benchmark | Command A | Gemma 3 27B |
|---|---|---|
| LMArena Text | 1331 | 1358 |
| LMArena Creative Writing | 1319 | 1346 |
| EQ-Bench Creative Writing | 1145 | 1266 |
| LMArena Multi-Turn | 1339 | 1345 |
| Short-Story Creative Writing | — | 79.9% |
| LiveBench Language | — | 34.6% |
Frequently asked questions
Is Command A better than Gemma 3 27B?
Command A is the stronger model overall, scoring 36.5 to 30.8 on the Noometry Index. Gemma 3 27B costs 44× less per token, which makes it the better buy when Command A's lead doesn't matter for your workload.
Which is cheaper, Command A or Gemma 3 27B?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or Gemma 3 27B better for coding?
Command A scores higher on coding benchmarks: 27.2 versus 22.5 in the Noometry coding category.
Which has the bigger context window?
Command A does, with 256K tokens against 131K.
How many benchmarks do Command A and Gemma 3 27B share?
24 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Gemma 3 27B has 43.