Model comparison
Command A vs Gemini 3 Flash Preview
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 35.9 on the Noometry Index.
Last verified . 20 shared benchmarks.
Cohere
GoogleSummary
- They share 20 benchmarks with published results for both. Command A scores higher in 0 categories and Gemini 3 Flash Preview in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 17.7.
- The biggest single-benchmark swing is LMCA: 10.3% for Command A and 43.1% for Gemini 3 Flash Preview.
- Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $2.50 / $10 for Command A.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 256K.
- Command A has downloadable open weights; the other is API-only.
Side by side
| Command A | Gemini 3 Flash Preview | |
|---|---|---|
| Provider | Cohere | |
| Noometry Index | 35.9 | 52.3 |
| Released | 2025-03-13 | 2025-12-17 |
| Weights | Open | Proprietary |
| Context window | 256K | 1.05M |
| Max output | 8K | 66K |
| Input $ / M tokens | $2.50 | $0.50 |
| Output $ / M tokens | $10 | $3 |
| Results tracked | 24 | 59 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Flash Preview leads
Command A: 26.8 (#317), Gemini 3 Flash Preview: 51.5 (#35)
| Benchmark | Command A | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Coding | 1331 | 1460 |
| SWE-bench Verified | — | 75.4% |
| SWE-bench Verified (bash only) | — | 75.8% |
| Aider Polyglot | 12% | — |
| LMArena WebDev | — | 1439 |
| SWE-bench Multilingual | — | 72.7% |
| GSO | — | 9.8% |
| WeirdML | — | 61.6% |
| ALE-Bench | — | 1,367 |
Agentic & Tool Use Gemini 3 Flash Preview leads
Command A: 35.7 (#36), Gemini 3 Flash Preview: 38.6 (#27)
| Benchmark | Command A | Gemini 3 Flash Preview |
|---|---|---|
| Terminal-Bench | — | 64.3% |
| Berkeley Function Calling Leaderboard | 57.1% | — |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 27.3% |
| τ²-bench Retail | — | 76.8% |
| τ²-bench Telecom | — | 91.2% |
| DeepResearch Bench | — | 49.8% |
| BALROG | — | 48.1% |
| GDP.pdf | — | 10% |
| LMArena Search | — | 1198 |
| Vending-Bench 2 | — | 3,635 |
Reasoning Gemini 3 Flash Preview leads
Command A: 17.7 (#276), Gemini 3 Flash Preview: 49.2 (#35)
| Benchmark | Command A | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1465 |
| DTBench | 61.3% | 89.1% |
| LMCA | 10.3% | 43.1% |
| ARC-AGI-2 | — | 33.6% |
| SimpleBench | — | 61.1% |
| Kagi LLM Benchmark | 28.8% | — |
| NYT Connections (extended) | — | 83.1% |
| ARC-AGI-1 | — | 84.7% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 26% |
| Epoch Capabilities Index | — | 151.83 |
| ForecastBench | — | 58.5 |
Math Gemini 3 Flash Preview leads
Command A: 33.5 (#172), Gemini 3 Flash Preview: 51.4 (#42)
| Benchmark | Command A | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Math | 1300 | 1472 |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 17.1% |
| MathArena Final-Answer Competitions | — | 67.6% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 15% |
| FrontierMath (Feb 2025 set) | — | 35.6% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Gemini 3 Flash Preview leads
Command A: 36.5 (#157), Gemini 3 Flash Preview: 58.8 (#30)
| Benchmark | Command A | Gemini 3 Flash Preview |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 13.5% |
| LMArena Expert | 1295 | 1461 |
| GPQA Diamond | — | 89.4% |
| SimpleQA Verified | — | 66.8% |
Multimodal Not comparable
Command A: —, Gemini 3 Flash Preview: 45.3 (#15)
| Benchmark | Command A | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Vision | — | 1285 |
| GeoBench | — | 88% |
| VPCT | — | 72.6% |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1413 |
Multilingual Gemini 3 Flash Preview leads
Command A: 45.5 (#166), Gemini 3 Flash Preview: 55.9 (#26)
| Benchmark | Command A | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Non-English | 1313 | 1458 |
| LMArena Chinese | 1327 | 1510 |
| LMArena French | 1352 | 1478 |
| LMArena German | 1341 | 1497 |
| LMArena Japanese | 1283 | 1488 |
| LMArena Korean | 1285 | 1443 |
| LMArena Russian | 1314 | 1480 |
| LMArena Spanish | 1346 | 1470 |
Instruction Following Gemini 3 Flash Preview leads
Command A: 69.3 (#172), Gemini 3 Flash Preview: 75.8 (#52)
| Benchmark | Command A | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Instruction Following | 1309 | 1437 |
Long Context Gemini 3 Flash Preview leads
Command A: 40.6 (#147), Gemini 3 Flash Preview: 44.4 (#63)
| Benchmark | Command A | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Longer Query | 1334 | 1452 |
Writing & Preference Gemini 3 Flash Preview leads
Command A: 47.8 (#204), Gemini 3 Flash Preview: 65.6 (#44)
| Benchmark | Command A | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Text | 1331 | 1466 |
| LMArena Creative Writing | 1319 | 1457 |
| LMArena Multi-Turn | 1338 | 1471 |
| EQ-Bench Creative Writing | 1145 | — |
Frequently asked questions
Is Command A better than Gemini 3 Flash Preview?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 35.9 on the Noometry Index.
Which is cheaper, Command A or Gemini 3 Flash Preview?
Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or Gemini 3 Flash Preview better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 51.5 versus 26.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 3 Flash Preview does, with 1.05M tokens against 256K.
How many benchmarks do Command A and Gemini 3 Flash Preview share?
20 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Gemini 3 Flash Preview has 59.