Model comparison
Command A vs o1-mini
Command A is the stronger model overall, scoring 36.5 to 34.0 on the Noometry Index.
Last verified . 18 shared benchmarks.
CohereSummary
- They share 18 benchmarks with published results for both. Command A scores higher in 7 categories and o1-mini in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Command A leads 35.9 to 24.6.
- The biggest single-benchmark swing is Aider Polyglot: 12% for Command A and 32.9% for o1-mini.
- Command A has downloadable open weights; the other is API-only.
Side by side
| Command A | o1-mini | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 36.5 | 34.0 |
| Released | 2025-03-13 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 24 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1-mini leads
Command A: 27.2 (#322), o1-mini: 35.5 (#224)
| Benchmark | Command A | o1-mini |
|---|---|---|
| Aider Polyglot | 12% | 32.9% |
| LMArena Coding | 1330 | 1362 |
| WeirdML | — | 36.3% |
| LiveBench Coding | — | 48% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use Command A leads
Command A: 35.9 (#40), o1-mini: 24.6 (#118)
| Benchmark | Command A | o1-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
| Cybench | — | 10% |
Reasoning Command A leads
Command A: 18.3 (#283), o1-mini: 8.8 (#346)
| Benchmark | Command A | o1-mini |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1333 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 18.1% |
| Kagi LLM Benchmark | 28.8% | — |
| ARC-AGI-1 | — | 14% |
| LiveBench Reasoning | — | 72.3% |
| DTBench | 61.3% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 10.3% | — |
| Epoch Capabilities Index | — | 135.82 |
| LiveBench | — | 57.8% |
Math Too close to call
Command A: 36.2 (#171), o1-mini: 35.4 (#186)
| Benchmark | Command A | o1-mini |
|---|---|---|
| LMArena Math | 1300 | 1358 |
| OTIS Mock AIME 2024-2025 | — | 46.9% |
| LiveBench Math | — | 62% |
| MATH Level 5 | — | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Command A leads
Command A: 37.1 (#159), o1-mini: 34.9 (#192)
| Benchmark | Command A | o1-mini |
|---|---|---|
| LMArena Expert | 1295 | 1316 |
| GPQA Diamond | — | 62.4% |
| Confabulations | — | 18.6% |
| Vectara Hallucination Rate | 9.3% | — |
Multilingual Command A leads
Command A: 45.3 (#170), o1-mini: 43.6 (#182)
| Benchmark | Command A | o1-mini |
|---|---|---|
| LMArena Non-English | 1313 | 1289 |
| LMArena Chinese | 1327 | 1314 |
| LMArena French | 1351 | 1293 |
| LMArena German | 1341 | 1278 |
| LMArena Japanese | 1285 | 1245 |
| LMArena Korean | 1285 | 1223 |
| LMArena Russian | 1314 | 1283 |
| LMArena Spanish | 1347 | 1303 |
Instruction Following Command A leads
Command A: 69.1 (#177), o1-mini: 66.7 (#206)
| Benchmark | Command A | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1309 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
Long Context Too close to call
Command A: 40.6 (#151), o1-mini: 40.1 (#161)
| Benchmark | Command A | o1-mini |
|---|---|---|
| LMArena Longer Query | 1334 | 1320 |
Writing & Preference Too close to call
Command A: 47.6 (#208), o1-mini: 48.4 (#202)
| Benchmark | Command A | o1-mini |
|---|---|---|
| LMArena Text | 1331 | 1317 |
| LMArena Creative Writing | 1319 | 1244 |
| LMArena Multi-Turn | 1339 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| EQ-Bench Creative Writing | 1145 | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is Command A better than o1-mini?
Command A is the stronger model overall, scoring 36.5 to 34.0 on the Noometry Index.
Is Command A or o1-mini better for coding?
o1-mini scores higher on coding benchmarks: 35.5 versus 27.2 in the Noometry coding category.
How many benchmarks do Command A and o1-mini share?
18 benchmarks have published results for both models. Command A has 24 scored results on Noometry and o1-mini has 39.