Model comparison
Command A vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 61.8 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-6 Sol in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 74.0 to 18.3.
- The biggest single-benchmark swing is LMCA: 10.3% for Command A and 59.1% for GPT-6 Sol.
- GPT-6 Sol is cheaper at $2 / $10 per million input/output tokens, against $2.50 / $10 for Command A.
- GPT-6 Sol 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-6 Sol | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 36.5 | 61.8 |
| Released | 2025-03-13 | 2026-09-22 |
| Weights | Open | Proprietary |
| Context window | 256K | 1.05M |
| Max output | 8K | 128K |
| Input $ / M tokens | $2.50 | $2 |
| Output $ / M tokens | $10 | $10 |
| Results tracked | 24 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
Command A: 27.2 (#322), GPT-6 Sol: 60.1 (#11)
| Benchmark | Command A | GPT-6 Sol |
|---|---|---|
| LMArena Coding | 1330 | 1447 |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| Aider Polyglot | 12% | — |
| LMArena WebDev | — | 1688 |
| SciCode | — | 57.6% |
| ALE-Bench | — | 2,462 |
Agentic & Tool Use GPT-6 Sol leads
Command A: 35.9 (#40), GPT-6 Sol: 37.2 (#36)
| Benchmark | Command A | GPT-6 Sol |
|---|---|---|
| APEX-Agents | — | 54.3% |
| Berkeley Function Calling Leaderboard | 57.1% | — |
| GDP.pdf | — | 26.4% |
| Vending-Bench 2 | — | 14,428 |
Reasoning GPT-6 Sol leads
Command A: 18.3 (#283), GPT-6 Sol: 74.0 (#9)
| Benchmark | Command A | GPT-6 Sol |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1418 |
| DTBench | 61.3% | 97.3% |
| LMCA | 10.3% | 59.1% |
| ARC-AGI-2 | — | 89.6% |
| Kagi LLM Benchmark | 28.8% | — |
| NYT Connections (extended) | — | 90.1% |
| ARC-AGI-1 | — | 95.5% |
| CritPt | — | 30.9% |
| EBR-Bench | — | 53.3% |
| Mystery Game Puzzles | — | 56% |
| Epoch Capabilities Index | — | 162.72 |
Math GPT-6 Sol leads
Command A: 36.2 (#171), GPT-6 Sol: 87.2 (#7)
| Benchmark | Command A | GPT-6 Sol |
|---|---|---|
| LMArena Math | 1300 | 1402 |
| FrontierMath (Tiers 1-3) | — | 89.8% |
| FrontierMath Tier 4 | — | 90% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 83% |
Knowledge GPT-6 Sol leads
Command A: 37.1 (#159), GPT-6 Sol: 64.8 (#15)
| Benchmark | Command A | GPT-6 Sol |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 6.5% |
| LMArena Expert | 1295 | 1439 |
| GPQA Diamond | — | 94.3% |
| SimpleQA Verified | — | 60.7% |
Multimodal Not comparable
Command A: —, GPT-6 Sol: 47.6 (#10)
| Benchmark | Command A | GPT-6 Sol |
|---|---|---|
| LMArena Vision | — | 1245 |
| Blueprint-Bench 2 | — | 36.9% |
| Furniture Assembly | — | 58.3% |
Multilingual GPT-6 Sol leads
Command A: 45.3 (#170), GPT-6 Sol: 50.5 (#118)
| Benchmark | Command A | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1313 | 1385 |
| LMArena Chinese | 1327 | 1405 |
| LMArena French | 1351 | 1410 |
| LMArena German | 1341 | 1390 |
| LMArena Japanese | 1285 | 1385 |
| LMArena Korean | 1285 | 1341 |
| LMArena Russian | 1314 | 1401 |
| LMArena Spanish | 1347 | 1384 |
Instruction Following GPT-6 Sol leads
Command A: 69.1 (#177), GPT-6 Sol: 74.5 (#94)
| Benchmark | Command A | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1309 | 1412 |
Long Context GPT-6 Sol leads
Command A: 40.6 (#151), GPT-6 Sol: 43.1 (#108)
| Benchmark | Command A | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1334 | 1411 |
Writing & Preference GPT-6 Sol leads
Command A: 47.6 (#208), GPT-6 Sol: 71.9 (#18)
| Benchmark | Command A | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1331 | 1395 |
| LMArena Creative Writing | 1319 | 1378 |
| EQ-Bench Creative Writing | 1145 | 2125 |
| LMArena Multi-Turn | 1339 | 1412 |
Frequently asked questions
Is Command A better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 36.5 on the Noometry Index.
Which is cheaper, Command A or GPT-6 Sol?
GPT-6 Sol is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 27.2 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 256K.
How many benchmarks do Command A and GPT-6 Sol share?
21 benchmarks have published results for both models. Command A has 24 scored results on Noometry and GPT-6 Sol has 45.