Model comparison
Command A vs Gemini 2.5 Flash
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 36.5 on the Noometry Index.
Last verified . 24 shared benchmarks.
Cohere
GoogleSummary
- They share 24 benchmarks with published results for both. Command A scores higher in 3 categories and Gemini 2.5 Flash in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Gemini 2.5 Flash leads 35.8 to 27.2.
- The biggest single-benchmark swing is Aider Polyglot: 12% for Command A and 55.1% for Gemini 2.5 Flash.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $2.50 / $10 for Command A.
- Gemini 2.5 Flash 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 2.5 Flash | |
|---|---|---|
| Provider | Cohere | |
| Noometry Index | 36.5 | 39.3 |
| Released | 2025-03-13 | 2025-04-17 |
| Weights | Open | Proprietary |
| Context window | 256K | 1.05M |
| Max output | 8K | 66K |
| Input $ / M tokens | $2.50 | $0.30 |
| Output $ / M tokens | $10 | $2.50 |
| Results tracked | 24 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Flash leads
Command A: 27.2 (#322), Gemini 2.5 Flash: 35.8 (#220)
| Benchmark | Command A | Gemini 2.5 Flash |
|---|---|---|
| Aider Polyglot | 12% | 55.1% |
| LMArena Coding | 1330 | 1424 |
| SWE-bench Verified (bash only) | — | 28.7% |
| WeirdML | — | 41.9% |
| ALE-Bench | — | 661.88 |
Agentic & Tool Use Command A leads
Command A: 35.9 (#40), Gemini 2.5 Flash: 30.8 (#74)
| Benchmark | Command A | Gemini 2.5 Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | 56.2% |
| Terminal-Bench | — | 17.1% |
| TheAgentCompany | — | 41.1% |
| BALROG | — | 33.5% |
| Vending-Bench 2 | — | 548.84 |
Reasoning Too close to call
Command A: 18.3 (#283), Gemini 2.5 Flash: 18.1 (#286)
| Benchmark | Command A | Gemini 2.5 Flash |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 56.8% |
| LMArena Hard Prompts | 1326 | 1422 |
| DTBench | 61.3% | 76.5% |
| LMCA | 10.3% | 27.5% |
| ARC-AGI-2 | — | 2.5% |
| SimpleBench | — | 41.2% |
| ARC-AGI-1 | — | 33.3% |
| CritPt | — | 1.1% |
| EnigmaEval | — | 2.7% |
| Epoch Capabilities Index | — | 143.03 |
| ForecastBench | — | 60.6 |
Math Gemini 2.5 Flash leads
Command A: 36.2 (#171), Gemini 2.5 Flash: 39.9 (#98)
| Benchmark | Command A | Gemini 2.5 Flash |
|---|---|---|
| LMArena Math | 1300 | 1415 |
| OTIS Mock AIME 2024-2025 | — | 73.1% |
| Omni-MATH | — | 38.5% |
| FrontierMath (Feb 2025 set) | — | 4.8% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Too close to call
Command A: 37.1 (#159), Gemini 2.5 Flash: 36.4 (#168)
| Benchmark | Command A | Gemini 2.5 Flash |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 7.8% |
| LMArena Expert | 1295 | 1426 |
| Humanity's Last Exam | — | 12.1% |
| MMLU-Pro | — | 63.9% |
| Confabulations | — | 16.8% |
| GPQA (HELM) | — | 39% |
Multimodal Not comparable
Command A: —, Gemini 2.5 Flash: 41.8 (#32)
| Benchmark | Command A | Gemini 2.5 Flash |
|---|---|---|
| LMArena Vision | — | 1253 |
| GeoBench | — | 76% |
| VPCT | — | 46.2% |
| SpatialViz-Bench | — | 36.9% |
Multilingual Gemini 2.5 Flash leads
Command A: 45.3 (#170), Gemini 2.5 Flash: 52.3 (#88)
| Benchmark | Command A | Gemini 2.5 Flash |
|---|---|---|
| LMArena Non-English | 1313 | 1409 |
| LMArena Chinese | 1327 | 1450 |
| LMArena French | 1351 | 1433 |
| LMArena German | 1341 | 1418 |
| LMArena Japanese | 1285 | 1405 |
| LMArena Korean | 1285 | 1385 |
| LMArena Russian | 1314 | 1415 |
| LMArena Spanish | 1347 | 1421 |
Instruction Following Gemini 2.5 Flash leads
Command A: 69.1 (#177), Gemini 2.5 Flash: 75.7 (#54)
| Benchmark | Command A | Gemini 2.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1309 | 1405 |
| IFEval | — | 89.8% |
Long Context Gemini 2.5 Flash leads
Command A: 40.6 (#151), Gemini 2.5 Flash: 47.5 (#17)
| Benchmark | Command A | Gemini 2.5 Flash |
|---|---|---|
| LMArena Longer Query | 1334 | 1419 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Gemini 2.5 Flash leads
Command A: 47.6 (#208), Gemini 2.5 Flash: 53.8 (#157)
| Benchmark | Command A | Gemini 2.5 Flash |
|---|---|---|
| LMArena Text | 1331 | 1417 |
| LMArena Creative Writing | 1319 | 1400 |
| EQ-Bench Creative Writing | 1145 | 1137 |
| LMArena Multi-Turn | 1339 | 1408 |
| Short-Story Creative Writing | — | 76.5% |
| WildBench | — | 81.7% |
Frequently asked questions
Is Command A better than Gemini 2.5 Flash?
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 36.5 on the Noometry Index.
Which is cheaper, Command A or Gemini 2.5 Flash?
Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or Gemini 2.5 Flash better for coding?
Gemini 2.5 Flash scores higher on coding benchmarks: 35.8 versus 27.2 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 256K.
How many benchmarks do Command A and Gemini 2.5 Flash share?
24 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Gemini 2.5 Flash has 54.