Model comparison
Command A vs gpt-oss-20b
Command A is the stronger model overall, scoring 36.5 to 32.5 on the Noometry Index. gpt-oss-20b costs 122× less per token, which makes it the better buy when Command A's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
CohereSummary
- They share 20 benchmarks with published results for both. Command A scores higher in 6 categories and gpt-oss-20b in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Command A leads 35.9 to 9.3.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 28.8% for Command A and 53.2% for gpt-oss-20b.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $2.50 / $10 for Command A.
- Command A accepts more context: 256K tokens versus 131K.
Side by side
| Command A | gpt-oss-20b | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 36.5 | 32.5 |
| Released | 2025-03-13 | 2025-08-05 |
| Weights | Open | Open |
| Context window | 256K | 131K |
| Max output | 8K | 16K |
| Input $ / M tokens | $2.50 | $0.018 |
| Output $ / M tokens | $10 | $0.09 |
| Results tracked | 24 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-20b leads
Command A: 27.2 (#322), gpt-oss-20b: 37.6 (#192)
| Benchmark | Command A | gpt-oss-20b |
|---|---|---|
| LMArena Coding | 1330 | 1306 |
| Aider Polyglot | 12% | — |
| SciCode | — | 34.4% |
| WeirdML | — | 40.9% |
| ALE-Bench | — | 566.05 |
Agentic & Tool Use Command A leads
Command A: 35.9 (#40), gpt-oss-20b: 9.3 (#154)
| Benchmark | Command A | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning Too close to call
Command A: 18.3 (#283), gpt-oss-20b: 19.3 (#261)
| Benchmark | Command A | gpt-oss-20b |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 53.2% |
| LMArena Hard Prompts | 1326 | 1274 |
| DTBench | 61.3% | 68% |
| LMCA | 10.3% | 14.5% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 4% |
| Epoch Capabilities Index | — | 137.82 |
Math gpt-oss-20b leads
Command A: 36.2 (#171), gpt-oss-20b: 39.4 (#103)
| Benchmark | Command A | gpt-oss-20b |
|---|---|---|
| LMArena Math | 1300 | 1317 |
| OTIS Mock AIME 2024-2025 | — | 65.3% |
| Omni-MATH | — | 56.5% |
Knowledge Command A leads
Command A: 37.1 (#159), gpt-oss-20b: 34.6 (#195)
| Benchmark | Command A | gpt-oss-20b |
|---|---|---|
| LMArena Expert | 1295 | 1258 |
| GPQA Diamond | — | 60.8% |
| MMLU-Pro | — | 74% |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | — | 59.4% |
Multilingual Command A leads
Command A: 45.3 (#170), gpt-oss-20b: 42.2 (#197)
| Benchmark | Command A | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 1313 | 1268 |
| LMArena Chinese | 1327 | 1314 |
| LMArena German | 1341 | 1255 |
| LMArena Japanese | 1285 | 1244 |
| LMArena Korean | 1285 | 1236 |
| LMArena Russian | 1314 | 1278 |
| LMArena Spanish | 1347 | 1267 |
| LMArena French | 1351 | — |
Instruction Following Command A leads
Command A: 69.1 (#177), gpt-oss-20b: 61.8 (#240)
| Benchmark | Command A | gpt-oss-20b |
|---|---|---|
| LMArena Instruction Following | 1309 | 1236 |
| IFEval | — | 73.2% |
Long Context Command A leads
Command A: 40.6 (#151), gpt-oss-20b: 37.9 (#209)
| Benchmark | Command A | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 1334 | 1250 |
Writing & Preference Command A leads
Command A: 47.6 (#208), gpt-oss-20b: 35.5 (#265)
| Benchmark | Command A | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1331 | 1287 |
| LMArena Creative Writing | 1319 | 1201 |
| EQ-Bench Creative Writing | 1145 | 666 |
| LMArena Multi-Turn | 1339 | 1268 |
| WildBench | — | 73.7% |
Frequently asked questions
Is Command A better than gpt-oss-20b?
Command A is the stronger model overall, scoring 36.5 to 32.5 on the Noometry Index. gpt-oss-20b costs 122× 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-oss-20b?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or gpt-oss-20b better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 27.2 in the Noometry coding category.
Which has the bigger context window?
Command A does, with 256K tokens against 131K.
How many benchmarks do Command A and gpt-oss-20b share?
20 benchmarks have published results for both models. Command A has 24 scored results on Noometry and gpt-oss-20b has 34.