Model comparison
Command A vs Gemma 4 31B IT
Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 35.9 on the Noometry Index.
Last verified . 19 shared benchmarks.
Cohere
GoogleSummary
- They share 19 benchmarks with published results for both. Command A scores higher in 0 categories and Gemma 4 31B IT in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Gemma 4 31B IT leads 41.9 to 26.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 28.8% for Command A and 63.5% for Gemma 4 31B IT.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $2.50 / $10 for Command A.
- Gemma 4 31B IT accepts more context: 262K tokens versus 256K.
Side by side
| Command A | Gemma 4 31B IT | |
|---|---|---|
| Provider | Cohere | |
| Noometry Index | 35.9 | 43.2 |
| Released | 2025-03-13 | 2026-04-02 |
| Weights | Open | Open |
| Context window | 256K | 262K |
| Max output | 8K | 33K |
| Input $ / M tokens | $2.50 | $0.09 |
| Output $ / M tokens | $10 | $0.34 |
| Results tracked | 24 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Command A: 26.8 (#317), Gemma 4 31B IT: 41.9 (#98)
| Benchmark | Command A | Gemma 4 31B IT |
|---|---|---|
| LMArena Coding | 1331 | 1459 |
| Aider Polyglot | 12% | — |
| LMArena WebDev | — | 1364 |
| SciCode | — | 43.4% |
| WeirdML | — | 52.3% |
| ALE-Bench | — | 925.5 |
Agentic & Tool Use Not comparable
Command A: 35.7 (#36), Gemma 4 31B IT: —
| Benchmark | Command A | Gemma 4 31B IT |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning Gemma 4 31B IT leads
Command A: 17.7 (#276), Gemma 4 31B IT: 26.4 (#119)
| Benchmark | Command A | Gemma 4 31B IT |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 63.5% |
| LMArena Hard Prompts | 1326 | 1448 |
| DTBench | 61.3% | 82.7% |
| LMCA | 10.3% | 39.3% |
| NYT Connections (extended) | — | 70.6% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 5% |
| Thematic Generalization | — | 53% |
| Surface Evolver Bench | — | 30.6% |
| Epoch Capabilities Index | — | 142.74 |
Math Gemma 4 31B IT leads
Command A: 33.5 (#172), Gemma 4 31B IT: 41.3 (#72)
| Benchmark | Command A | Gemma 4 31B IT |
|---|---|---|
| LMArena Math | 1300 | 1464 |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
Knowledge Gemma 4 31B IT leads
Command A: 36.5 (#157), Gemma 4 31B IT: 37.9 (#141)
| Benchmark | Command A | Gemma 4 31B IT |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 7.4% |
| LMArena Expert | 1295 | 1465 |
| GPQA Diamond | — | 75.8% |
| SimpleQA Verified | — | 10.4% |
Multimodal Not comparable
Command A: —, Gemma 4 31B IT: 41.0 (#32)
| Benchmark | Command A | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | — | 1278 |
| LMArena Document | — | 1425 |
Multilingual Gemma 4 31B IT leads
Command A: 45.5 (#166), Gemma 4 31B IT: 54.0 (#52)
| Benchmark | Command A | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1313 | 1431 |
| LMArena Chinese | 1327 | 1478 |
| LMArena French | 1352 | 1436 |
| LMArena Russian | 1314 | 1462 |
| LMArena Spanish | 1346 | 1443 |
| LMArena German | 1341 | — |
| LMArena Japanese | 1283 | — |
| LMArena Korean | 1285 | — |
Instruction Following Gemma 4 31B IT leads
Command A: 69.3 (#172), Gemma 4 31B IT: 75.6 (#58)
| Benchmark | Command A | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1309 | 1433 |
Long Context Gemma 4 31B IT leads
Command A: 40.6 (#147), Gemma 4 31B IT: 44.2 (#67)
| Benchmark | Command A | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1334 | 1446 |
Writing & Preference Gemma 4 31B IT leads
Command A: 47.8 (#204), Gemma 4 31B IT: 60.7 (#92)
| Benchmark | Command A | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1331 | 1443 |
| LMArena Creative Writing | 1319 | 1416 |
| EQ-Bench Creative Writing | 1145 | 1368 |
| LMArena Multi-Turn | 1338 | 1452 |
| EQ-Bench 4 | — | 1120 |
Frequently asked questions
Is Command A better than Gemma 4 31B IT?
Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 35.9 on the Noometry Index.
Which is cheaper, Command A or Gemma 4 31B IT?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or Gemma 4 31B IT better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 41.9 versus 26.8 in the Noometry coding category.
Which has the bigger context window?
Gemma 4 31B IT does, with 262K tokens against 256K.
How many benchmarks do Command A and Gemma 4 31B IT share?
19 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Gemma 4 31B IT has 35.