Model comparison
Command A vs GPT-5.6 Terra
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 36.5 on the Noometry Index.
Last verified . 21 shared benchmarks.
CohereSummary
- They share 21 benchmarks with published results for both. Command A scores higher in 0 categories and GPT-5.6 Terra in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Terra leads 81.6 to 36.2.
- The biggest single-benchmark swing is LMCA: 10.3% for Command A and 55% for GPT-5.6 Terra.
- Both cost about the same: $2.50 input and $10 output per million tokens.
- GPT-5.6 Terra accepts more context: 1.05M tokens versus 256K.
- Command A has downloadable open weights; the other is API-only.
Side by side
| Command A | GPT-5.6 Terra | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 36.5 | 59.2 |
| Released | 2025-03-13 | 2026-07-09 |
| Weights | Open | Proprietary |
| Context window | 256K | 1.05M |
| Max output | 8K | 128K |
| Input $ / M tokens | $2.50 | $2 |
| Output $ / M tokens | $10 | $12 |
| Results tracked | 24 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Terra leads
Command A: 27.2 (#322), GPT-5.6 Terra: 57.7 (#19)
| Benchmark | Command A | GPT-5.6 Terra |
|---|---|---|
| LMArena Coding | 1330 | 1484 |
| DeepSWE | — | 69.6% |
| FrontierCode | — | 41.3% |
| Aider Polyglot | 12% | — |
| CursorBench | — | 41.3% |
| LMArena WebDev | — | 1522 |
| SciCode | — | 55% |
| WeirdML | — | 78.3% |
| ALE-Bench | — | 1,951 |
Agentic & Tool Use GPT-5.6 Terra leads
Command A: 35.9 (#40), GPT-5.6 Terra: 40.1 (#25)
| Benchmark | Command A | GPT-5.6 Terra |
|---|---|---|
| APEX-Agents | — | 58.2% |
| Berkeley Function Calling Leaderboard | 57.1% | — |
| BALROG | — | 53.2% |
| GDP.pdf | — | 24.7% |
| Vending-Bench 2 | — | 7,343 |
Reasoning GPT-5.6 Terra leads
Command A: 18.3 (#283), GPT-5.6 Terra: 60.7 (#21)
| Benchmark | Command A | GPT-5.6 Terra |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 51.3% |
| LMArena Hard Prompts | 1326 | 1468 |
| DTBench | 61.3% | 93.3% |
| LMCA | 10.3% | 55% |
| ARC-AGI-2 | — | 83.9% |
| SimpleBench | — | 48.9% |
| NYT Connections (extended) | — | 78.4% |
| ARC-AGI-1 | — | 96.5% |
| CritPt | — | 30% |
| Chess Puzzles | — | 54% |
| Mystery Game Puzzles | — | 35% |
| Surface Evolver Bench | — | 83.8% |
| Epoch Capabilities Index | — | 159.62 |
Math GPT-5.6 Terra leads
Command A: 36.2 (#171), GPT-5.6 Terra: 81.6 (#12)
| Benchmark | Command A | GPT-5.6 Terra |
|---|---|---|
| LMArena Math | 1300 | 1466 |
| FrontierMath (Tiers 1-3) | — | 86% |
| FrontierMath Tier 4 | — | 70.7% |
| OTIS Mock AIME 2024-2025 | — | 99.7% |
| ProofBench | — | 74% |
Knowledge GPT-5.6 Terra leads
Command A: 37.1 (#159), GPT-5.6 Terra: 61.2 (#30)
| Benchmark | Command A | GPT-5.6 Terra |
|---|---|---|
| LMArena Expert | 1295 | 1492 |
| GPQA Diamond | — | 93.3% |
| SimpleQA Verified | — | 43.2% |
| Vectara Hallucination Rate | 9.3% | — |
Multimodal Not comparable
Command A: —, GPT-5.6 Terra: 47.3 (#11)
| Benchmark | Command A | GPT-5.6 Terra |
|---|---|---|
| LMArena Vision | — | 1271 |
| Blueprint-Bench 2 | — | 30.8% |
| Furniture Assembly | — | 54.2% |
| LMArena Document | — | 1472 |
Multilingual GPT-5.6 Terra leads
Command A: 45.3 (#170), GPT-5.6 Terra: 54.4 (#44)
| Benchmark | Command A | GPT-5.6 Terra |
|---|---|---|
| LMArena Non-English | 1313 | 1439 |
| LMArena Chinese | 1327 | 1513 |
| LMArena French | 1351 | 1471 |
| LMArena German | 1341 | 1460 |
| LMArena Japanese | 1285 | 1457 |
| LMArena Korean | 1285 | 1425 |
| LMArena Russian | 1314 | 1450 |
| LMArena Spanish | 1347 | 1448 |
Instruction Following GPT-5.6 Terra leads
Command A: 69.1 (#177), GPT-5.6 Terra: 76.4 (#40)
| Benchmark | Command A | GPT-5.6 Terra |
|---|---|---|
| LMArena Instruction Following | 1309 | 1454 |
Long Context GPT-5.6 Terra leads
Command A: 40.6 (#151), GPT-5.6 Terra: 44.4 (#68)
| Benchmark | Command A | GPT-5.6 Terra |
|---|---|---|
| LMArena Longer Query | 1334 | 1451 |
Writing & Preference GPT-5.6 Terra leads
Command A: 47.6 (#208), GPT-5.6 Terra: 70.2 (#23)
| Benchmark | Command A | GPT-5.6 Terra |
|---|---|---|
| LMArena Text | 1331 | 1447 |
| LMArena Creative Writing | 1319 | 1410 |
| EQ-Bench Creative Writing | 1145 | 1855 |
| LMArena Multi-Turn | 1339 | 1449 |
| EQ-Bench 4 | — | 1234 |
Frequently asked questions
Is Command A better than GPT-5.6 Terra?
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 36.5 on the Noometry Index.
Which is cheaper, Command A or GPT-5.6 Terra?
Command A is cheaper. It lists at $2.50 per million input tokens and $10 per million output tokens; GPT-5.6 Terra lists at $2 and $12.
Is Command A or GPT-5.6 Terra better for coding?
GPT-5.6 Terra scores higher on coding benchmarks: 57.7 versus 27.2 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Terra does, with 1.05M tokens against 256K.
How many benchmarks do Command A and GPT-5.6 Terra share?
21 benchmarks have published results for both models. Command A has 24 scored results on Noometry and GPT-5.6 Terra has 52.