Model comparison
Command A vs GPT-5 Mini
GPT-5 Mini is the stronger model overall, scoring 41.8 to 36.5 on the Noometry Index.
Last verified . 23 shared benchmarks.
CohereSummary
- They share 23 benchmarks with published results for both. Command A scores higher in 1 category and GPT-5 Mini in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-5 Mini leads 40.1 to 27.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 28.8% for Command A and 70.3% for GPT-5 Mini.
- GPT-5 Mini is cheaper at $0.25 / $2 per million input/output tokens, against $2.50 / $10 for Command A.
- GPT-5 Mini accepts more context: 400K tokens versus 256K.
- Command A has downloadable open weights; the other is API-only.
Side by side
| Command A | GPT-5 Mini | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 36.5 | 41.8 |
| Released | 2025-03-13 | 2025-08-07 |
| Weights | Open | Proprietary |
| Context window | 256K | 400K |
| Max output | 8K | 128K |
| Input $ / M tokens | $2.50 | $0.25 |
| Output $ / M tokens | $10 | $2 |
| Results tracked | 24 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Mini leads
Command A: 27.2 (#322), GPT-5 Mini: 40.1 (#146)
| Benchmark | Command A | GPT-5 Mini |
|---|---|---|
| LMArena Coding | 1330 | 1406 |
| SWE-bench Verified | — | 64.7% |
| SWE-bench Verified (bash only) | — | 59.8% |
| Aider Polyglot | 12% | — |
| SWE-bench Multilingual | — | 39.7% |
| SciCode | — | 39.2% |
| WeirdML | — | 52.7% |
| ALE-Bench | — | 799.77 |
| AlgoTune | — | 1.38 |
Agentic & Tool Use Command A leads
Command A: 35.9 (#40), GPT-5 Mini: 31.1 (#70)
| Benchmark | Command A | GPT-5 Mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | 55.5% |
| Terminal-Bench | — | 34.8% |
| Vending-Bench 2 | — | -31.18 |
Reasoning GPT-5 Mini leads
Command A: 18.3 (#283), GPT-5 Mini: 23.9 (#168)
| Benchmark | Command A | GPT-5 Mini |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 70.3% |
| LMArena Hard Prompts | 1326 | 1380 |
| DTBench | 61.3% | 80.5% |
| LMCA | 10.3% | 34.2% |
| ARC-AGI-2 | — | 4.4% |
| ARC-AGI-1 | — | 54.3% |
| CritPt | — | 0% |
| Chess Puzzles | — | 30% |
| EnigmaEval | — | 8.2% |
| Mystery Game Puzzles | — | 10% |
| Epoch Capabilities Index | — | 145.52 |
| ForecastBench | — | 61 |
Math GPT-5 Mini leads
Command A: 36.2 (#171), GPT-5 Mini: 46.7 (#69)
| Benchmark | Command A | GPT-5 Mini |
|---|---|---|
| LMArena Math | 1300 | 1378 |
| FrontierMath (Tiers 1-3) | — | 46.7% |
| FrontierMath Tier 4 | — | 12.2% |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 9% |
| Omni-MATH | — | 72.2% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 27.2% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge GPT-5 Mini leads
Command A: 37.1 (#159), GPT-5 Mini: 45.6 (#86)
| Benchmark | Command A | GPT-5 Mini |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 12.9% |
| LMArena Expert | 1295 | 1379 |
| GPQA Diamond | — | 75% |
| Humanity's Last Exam | — | 19.4% |
| SimpleQA Verified | — | 21.6% |
| MMLU-Pro | — | 83.5% |
| Confabulations | — | 13.3% |
| GPQA (HELM) | — | 75.6% |
Multimodal Not comparable
Command A: —, GPT-5 Mini: 35.6 (#85)
| Benchmark | Command A | GPT-5 Mini |
|---|---|---|
| LMArena Vision | — | 1202 |
| VPCT | — | 40.2% |
Multilingual GPT-5 Mini leads
Command A: 45.3 (#170), GPT-5 Mini: 48.9 (#137)
| Benchmark | Command A | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | 1313 | 1363 |
| LMArena Chinese | 1327 | 1385 |
| LMArena French | 1351 | 1386 |
| LMArena German | 1341 | 1366 |
| LMArena Japanese | 1285 | 1341 |
| LMArena Korean | 1285 | 1308 |
| LMArena Russian | 1314 | 1362 |
| LMArena Spanish | 1347 | 1355 |
Instruction Following GPT-5 Mini leads
Command A: 69.1 (#177), GPT-5 Mini: 76.2 (#46)
| Benchmark | Command A | GPT-5 Mini |
|---|---|---|
| LMArena Instruction Following | 1309 | 1357 |
| IFEval | — | 92.7% |
Long Context GPT-5 Mini leads
Command A: 40.6 (#151), GPT-5 Mini: 41.9 (#132)
| Benchmark | Command A | GPT-5 Mini |
|---|---|---|
| LMArena Longer Query | 1334 | 1355 |
| Fiction.LiveBench | — | 69.4% |
Writing & Preference GPT-5 Mini leads
Command A: 47.6 (#208), GPT-5 Mini: 55.2 (#148)
| Benchmark | Command A | GPT-5 Mini |
|---|---|---|
| LMArena Text | 1331 | 1373 |
| LMArena Creative Writing | 1319 | 1325 |
| EQ-Bench Creative Writing | 1145 | 1313 |
| LMArena Multi-Turn | 1339 | 1363 |
| Short-Story Creative Writing | — | 83.1% |
| WildBench | — | 85.5% |
Frequently asked questions
Is Command A better than GPT-5 Mini?
GPT-5 Mini is the stronger model overall, scoring 41.8 to 36.5 on the Noometry Index.
Which is cheaper, Command A or GPT-5 Mini?
GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or GPT-5 Mini better for coding?
GPT-5 Mini scores higher on coding benchmarks: 40.1 versus 27.2 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Mini does, with 400K tokens against 256K.
How many benchmarks do Command A and GPT-5 Mini share?
23 benchmarks have published results for both models. Command A has 24 scored results on Noometry and GPT-5 Mini has 60.