Model comparison
Command A vs GPT-4o mini
Command A is the stronger model overall, scoring 36.5 to 25.5 on the Noometry Index. GPT-4o mini costs 17× less per token, which makes it the better buy when Command A's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
CohereSummary
- They share 22 benchmarks with published results for both. Command A scores higher in 9 categories and GPT-4o mini in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Command A leads 36.2 to 10.4.
- The biggest single-benchmark swing is Aider Polyglot: 12% for Command A and 3.6% for GPT-4o mini.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $2.50 / $10 for Command A.
- Command A accepts more context: 256K tokens versus 128K.
- Command A has downloadable open weights; the other is API-only.
Side by side
| Command A | GPT-4o mini | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 36.5 | 25.5 |
| Released | 2025-03-13 | 2024-07-18 |
| Weights | Open | Proprietary |
| Context window | 256K | 128K |
| Max output | 8K | 16K |
| Input $ / M tokens | $2.50 | $0.15 |
| Output $ / M tokens | $10 | $0.60 |
| Results tracked | 24 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Command A leads
Command A: 27.2 (#322), GPT-4o mini: 22.0 (#335)
| Benchmark | Command A | GPT-4o mini |
|---|---|---|
| Aider Polyglot | 12% | 3.6% |
| LMArena Coding | 1330 | 1290 |
| WeirdML | — | 11.8% |
| BigCodeBench Instruct | — | 46.1% |
| LiveBench Coding | — | 43.1% |
| BigCodeBench Complete | — | 57.4% |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 72.2% |
Agentic & Tool Use Command A leads
Command A: 35.9 (#40), GPT-4o mini: 27.5 (#101)
| Benchmark | Command A | GPT-4o mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
| BALROG | — | 17.4% |
Reasoning Command A leads
Command A: 18.3 (#283), GPT-4o mini: 8.7 (#347)
| Benchmark | Command A | GPT-4o mini |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 28.8% |
| LMArena Hard Prompts | 1326 | 1267 |
| DTBench | 61.3% | 54.4% |
| LMCA | 10.3% | 10.4% |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 10.7% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 32.8% |
| Mystery Game Puzzles | — | 12% |
| LiveBench Data Analysis | — | 50% |
| Epoch Capabilities Index | — | 126.56 |
| LiveBench | — | 41.3% |
| PIQA | — | 88.7% |
Math Command A leads
Command A: 36.2 (#171), GPT-4o mini: 10.4 (#314)
| Benchmark | Command A | GPT-4o mini |
|---|---|---|
| LMArena Math | 1300 | 1267 |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| OTIS Mock AIME 2024-2025 | — | 6.9% |
| Omni-MATH | — | 28% |
| LiveBench Math | — | 36.3% |
| MATH Level 5 | — | 52.6% |
| GSM8K | — | 91.3% |
Knowledge Command A leads
Command A: 37.1 (#159), GPT-4o mini: 17.7 (#284)
| Benchmark | Command A | GPT-4o mini |
|---|---|---|
| LMArena Expert | 1295 | 1235 |
| GPQA Diamond | — | 37.7% |
| SimpleQA Verified | — | 8.3% |
| MMLU-Pro | — | 60.3% |
| Confabulations | — | 37.2% |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | — | 36.8% |
| BoolQ | — | 88.7% |
| MMLU | — | 81.8% |
Multimodal Not comparable
Command A: —, GPT-4o mini: 25.9 (#122)
| Benchmark | Command A | GPT-4o mini |
|---|---|---|
| LMArena Vision | — | 1066 |
| Video-MME | — | 64.8% |
| GeoBench | — | 64% |
| VPCT | — | 34% |
Multilingual Command A leads
Command A: 45.3 (#170), GPT-4o mini: 42.0 (#199)
| Benchmark | Command A | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1313 | 1266 |
| LMArena Chinese | 1327 | 1265 |
| LMArena French | 1351 | 1297 |
| LMArena German | 1341 | 1272 |
| LMArena Japanese | 1285 | 1216 |
| LMArena Korean | 1285 | 1195 |
| LMArena Russian | 1314 | 1275 |
| LMArena Spanish | 1347 | 1276 |
Instruction Following Command A leads
Command A: 69.1 (#177), GPT-4o mini: 61.9 (#239)
| Benchmark | Command A | GPT-4o mini |
|---|---|---|
| LMArena Instruction Following | 1309 | 1258 |
| LiveBench Instruction Following | — | 56.8% |
| IFEval | — | 78.2% |
Long Context Command A leads
Command A: 40.6 (#151), GPT-4o mini: 39.1 (#186)
| Benchmark | Command A | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1334 | 1289 |
Writing & Preference Command A leads
Command A: 47.6 (#208), GPT-4o mini: 39.5 (#248)
| Benchmark | Command A | GPT-4o mini |
|---|---|---|
| LMArena Text | 1331 | 1286 |
| LMArena Creative Writing | 1319 | 1268 |
| EQ-Bench Creative Writing | 1145 | 873 |
| LMArena Multi-Turn | 1339 | 1285 |
| Short-Story Creative Writing | — | 67.2% |
| WildBench | — | 79.1% |
| LiveBench Language | — | 28.6% |
Frequently asked questions
Is Command A better than GPT-4o mini?
Command A is the stronger model overall, scoring 36.5 to 25.5 on the Noometry Index. GPT-4o mini costs 17× less per token, which makes it the better buy when Command A's lead doesn't matter for your workload.
Which is cheaper, Command A or GPT-4o mini?
GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or GPT-4o mini better for coding?
Command A scores higher on coding benchmarks: 27.2 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
Command A does, with 256K tokens against 128K.
How many benchmarks do Command A and GPT-4o mini share?
22 benchmarks have published results for both models. Command A has 24 scored results on Noometry and GPT-4o mini has 60.