Model comparison
Command A vs o3-mini
Command A and o3-mini score almost the same on the Noometry Index (36.5 vs 36.7), so choose on price, context window or the category you care about most.
Last verified . 20 shared benchmarks.
CohereSummary
- They share 20 benchmarks with published results for both. Command A scores higher in 4 categories and o3-mini in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where o3-mini leads 40.8 to 27.2.
- The biggest single-benchmark swing is Aider Polyglot: 12% for Command A and 60.4% for o3-mini.
- o3-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $2.50 / $10 for Command A.
- Command A accepts more context: 256K tokens versus 200K.
- Command A has downloadable open weights; the other is API-only.
Side by side
| Command A | o3-mini | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 36.5 | 36.7 |
| Released | 2025-03-13 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | 256K | 200K |
| Max output | 8K | 100K |
| Input $ / M tokens | $2.50 | $1.10 |
| Output $ / M tokens | $10 | $4.40 |
| Results tracked | 24 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Command A: 27.2 (#322), o3-mini: 40.8 (#132)
| Benchmark | Command A | o3-mini |
|---|---|---|
| Aider Polyglot | 12% | 60.4% |
| LMArena Coding | 1330 | 1378 |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| WeirdML | — | 43.7% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
Agentic & Tool Use Command A leads
Command A: 35.9 (#40), o3-mini: 29.6 (#84)
| Benchmark | Command A | o3-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
| Cybench | — | 22.5% |
Reasoning Command A leads
Command A: 18.3 (#283), o3-mini: 16.3 (#305)
| Benchmark | Command A | o3-mini |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1366 |
| DTBench | 61.3% | 68.8% |
| LMCA | 10.3% | 19% |
| ARC-AGI-2 | — | 3% |
| SimpleBench | — | 22.8% |
| Kagi LLM Benchmark | 28.8% | — |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 17% |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| LiveBench Data Analysis | — | 70.6% |
| Epoch Capabilities Index | — | 140.34 |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |
Math Command A leads
Command A: 36.2 (#171), o3-mini: 28.1 (#244)
| Benchmark | Command A | o3-mini |
|---|---|---|
| LMArena Math | 1300 | 1396 |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 76.9% |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge o3-mini leads
Command A: 37.1 (#159), o3-mini: 38.3 (#146)
| Benchmark | Command A | o3-mini |
|---|---|---|
| LMArena Expert | 1295 | 1364 |
| GPQA Diamond | — | 77% |
| SimpleQA Verified | — | 15.3% |
| Confabulations | — | 17.9% |
| Vectara Hallucination Rate | 9.3% | — |
Multilingual Too close to call
Command A: 45.3 (#170), o3-mini: 45.7 (#164)
| Benchmark | Command A | o3-mini |
|---|---|---|
| LMArena Non-English | 1313 | 1319 |
| LMArena Chinese | 1327 | 1379 |
| LMArena French | 1351 | 1334 |
| LMArena German | 1341 | 1303 |
| LMArena Japanese | 1285 | 1286 |
| LMArena Korean | 1285 | 1314 |
| LMArena Russian | 1314 | 1304 |
| LMArena Spanish | 1347 | 1321 |
Instruction Following o3-mini leads
Command A: 69.1 (#177), o3-mini: 75.1 (#72)
| Benchmark | Command A | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1309 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
Long Context Command A leads
Command A: 40.6 (#151), o3-mini: 33.8 (#256)
| Benchmark | Command A | o3-mini |
|---|---|---|
| LMArena Longer Query | 1334 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference o3-mini leads
Command A: 47.6 (#208), o3-mini: 50.3 (#182)
| Benchmark | Command A | o3-mini |
|---|---|---|
| LMArena Text | 1331 | 1337 |
| LMArena Creative Writing | 1319 | 1286 |
| LMArena Multi-Turn | 1339 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| EQ-Bench Creative Writing | 1145 | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Command A better than o3-mini?
Command A and o3-mini score almost the same on the Noometry Index (36.5 vs 36.7), so choose on price, context window or the category you care about most.
Which is cheaper, Command A or o3-mini?
o3-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 27.2 in the Noometry coding category.
Which has the bigger context window?
Command A does, with 256K tokens against 200K.
How many benchmarks do Command A and o3-mini share?
20 benchmarks have published results for both models. Command A has 24 scored results on Noometry and o3-mini has 51.