Model comparison
Command A vs GPT-5.4 mini
GPT-5.4 mini is the stronger model overall, scoring 44.8 to 35.9 on the Noometry Index.
Last verified . 22 shared benchmarks.
CohereSummary
- They share 22 benchmarks with published results for both. Command A scores higher in 1 category and GPT-5.4 mini in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-5.4 mini leads 45.0 to 26.8.
- The biggest single-benchmark swing is LMCA: 10.3% for Command A and 40.8% for GPT-5.4 mini.
- GPT-5.4 mini is cheaper at $0.75 / $4.50 per million input/output tokens, against $2.50 / $10 for Command A.
- GPT-5.4 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-5.4 mini | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 35.9 | 44.8 |
| Released | 2025-03-13 | 2026-03-17 |
| Weights | Open | Proprietary |
| Context window | 256K | 400K |
| Max output | 8K | 128K |
| Input $ / M tokens | $2.50 | $0.75 |
| Output $ / M tokens | $10 | $4.50 |
| Results tracked | 24 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
Command A: 26.8 (#317), GPT-5.4 mini: 45.0 (#67)
| Benchmark | Command A | GPT-5.4 mini |
|---|---|---|
| LMArena Coding | 1331 | 1438 |
| FrontierCode | — | 27% |
| Aider Polyglot | 12% | — |
| LMArena WebDev | — | 1397 |
| SciCode | — | 49.9% |
| WeirdML | — | 60.3% |
| ALE-Bench | — | 1,189 |
Agentic & Tool Use Command A leads
Command A: 35.7 (#36), GPT-5.4 mini: 29.6 (#74)
| Benchmark | Command A | GPT-5.4 mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
| DeepResearch Bench | — | 36.3% |
Reasoning GPT-5.4 mini leads
Command A: 17.7 (#276), GPT-5.4 mini: 30.3 (#77)
| Benchmark | Command A | GPT-5.4 mini |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 37.9% |
| LMArena Hard Prompts | 1326 | 1424 |
| DTBench | 61.3% | 80% |
| LMCA | 10.3% | 40.8% |
| ARC-AGI-2 | — | 18.9% |
| NYT Connections (extended) | — | 61.8% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | — | 10% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 61.7% |
| Mystery Game Puzzles | — | 11% |
| Epoch Capabilities Index | — | 148.83 |
| ForecastBench | — | 57 |
Math GPT-5.4 mini leads
Command A: 33.5 (#172), GPT-5.4 mini: 45.4 (#63)
| Benchmark | Command A | GPT-5.4 mini |
|---|---|---|
| LMArena Math | 1300 | 1418 |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 9.8% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 21% |
| FrontierMath (Feb 2025 set) | — | 28.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GPT-5.4 mini leads
Command A: 36.5 (#157), GPT-5.4 mini: 51.4 (#62)
| Benchmark | Command A | GPT-5.4 mini |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 5.5% |
| LMArena Expert | 1295 | 1434 |
| GPQA Diamond | — | 86.9% |
| SimpleQA Verified | — | 29.4% |
Multimodal Not comparable
Command A: —, GPT-5.4 mini: 39.0 (#51)
| Benchmark | Command A | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual GPT-5.4 mini leads
Command A: 45.5 (#166), GPT-5.4 mini: 52.1 (#94)
| Benchmark | Command A | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1313 | 1405 |
| LMArena Chinese | 1327 | 1446 |
| LMArena French | 1352 | 1440 |
| LMArena German | 1341 | 1407 |
| LMArena Japanese | 1283 | 1375 |
| LMArena Korean | 1285 | 1369 |
| LMArena Russian | 1314 | 1417 |
| LMArena Spanish | 1346 | 1403 |
Instruction Following GPT-5.4 mini leads
Command A: 69.3 (#172), GPT-5.4 mini: 74.3 (#99)
| Benchmark | Command A | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1309 | 1405 |
Long Context GPT-5.4 mini leads
Command A: 40.6 (#147), GPT-5.4 mini: 42.9 (#107)
| Benchmark | Command A | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1334 | 1407 |
Writing & Preference GPT-5.4 mini leads
Command A: 47.8 (#204), GPT-5.4 mini: 64.2 (#56)
| Benchmark | Command A | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1331 | 1411 |
| LMArena Creative Writing | 1319 | 1370 |
| EQ-Bench Creative Writing | 1145 | 1665 |
| LMArena Multi-Turn | 1338 | 1429 |
Frequently asked questions
Is Command A better than GPT-5.4 mini?
GPT-5.4 mini is the stronger model overall, scoring 44.8 to 35.9 on the Noometry Index.
Which is cheaper, Command A or GPT-5.4 mini?
GPT-5.4 mini is cheaper. It lists at $0.75 per million input tokens and $4.50 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or GPT-5.4 mini better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 26.8 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 mini does, with 400K tokens against 256K.
How many benchmarks do Command A and GPT-5.4 mini share?
22 benchmarks have published results for both models. Command A has 24 scored results on Noometry and GPT-5.4 mini has 46.