Model comparison
Command A vs Gemini 3 Deep Think
Command A has enough public results to be ranked (#212); Gemini 3 Deep Think does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Cohere
GoogleSummary
- The widest gap is in reasoning, where Gemini 3 Deep Think leads 70.8 to 17.7.
- Command A has downloadable open weights; the other is API-only.
Side by side
| Command A | Gemini 3 Deep Think | |
|---|---|---|
| Provider | Cohere | |
| Noometry Index | 35.9 | 58.5 |
| Released | 2025-03-13 | 2026-02-12 |
| Weights | Open | Proprietary |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 24 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Command A: 26.8 (#317), Gemini 3 Deep Think: —
| Benchmark | Command A | Gemini 3 Deep Think |
|---|---|---|
| Aider Polyglot | 12% | — |
| LMArena Coding | 1331 | — |
Agentic & Tool Use Not comparable
Command A: 35.7 (#36), Gemini 3 Deep Think: —
| Benchmark | Command A | Gemini 3 Deep Think |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning Gemini 3 Deep Think leads
Command A: 17.7 (#276), Gemini 3 Deep Think: 70.8 (#11)
| Benchmark | Command A | Gemini 3 Deep Think |
|---|---|---|
| ARC-AGI-2 | — | 84.6% |
| Kagi LLM Benchmark | 28.8% | — |
| ARC-AGI-1 | — | 96% |
| CritPt | — | 25.7% |
| LMArena Hard Prompts | 1326 | — |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |
Math Not comparable
Command A: 33.5 (#172), Gemini 3 Deep Think: —
| Benchmark | Command A | Gemini 3 Deep Think |
|---|---|---|
| LMArena Math | 1300 | — |
Knowledge Not comparable
Command A: 36.5 (#157), Gemini 3 Deep Think: —
| Benchmark | Command A | Gemini 3 Deep Think |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | — |
| LMArena Expert | 1295 | — |
Multilingual Not comparable
Command A: 45.5 (#166), Gemini 3 Deep Think: —
| Benchmark | Command A | Gemini 3 Deep Think |
|---|---|---|
| LMArena Non-English | 1313 | — |
| LMArena Chinese | 1327 | — |
| LMArena French | 1352 | — |
| LMArena German | 1341 | — |
| LMArena Japanese | 1283 | — |
| LMArena Korean | 1285 | — |
| LMArena Russian | 1314 | — |
| LMArena Spanish | 1346 | — |
Instruction Following Not comparable
Command A: 69.3 (#172), Gemini 3 Deep Think: —
| Benchmark | Command A | Gemini 3 Deep Think |
|---|---|---|
| LMArena Instruction Following | 1309 | — |
Long Context Not comparable
Command A: 40.6 (#147), Gemini 3 Deep Think: —
| Benchmark | Command A | Gemini 3 Deep Think |
|---|---|---|
| LMArena Longer Query | 1334 | — |
Writing & Preference Not comparable
Command A: 47.8 (#204), Gemini 3 Deep Think: —
| Benchmark | Command A | Gemini 3 Deep Think |
|---|---|---|
| LMArena Text | 1331 | — |
| LMArena Creative Writing | 1319 | — |
| EQ-Bench Creative Writing | 1145 | — |
| LMArena Multi-Turn | 1338 | — |
Frequently asked questions
Is Command A better than Gemini 3 Deep Think?
Command A has enough public results to be ranked (#212); Gemini 3 Deep Think does not yet, so treat this comparison as directional.
How many benchmarks do Command A and Gemini 3 Deep Think share?
0 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Gemini 3 Deep Think has 3.