Model comparison
Command R+ vs gpt-oss-20b
Command R+ and gpt-oss-20b score almost the same on the Noometry Index (32.4 vs 32.5), so choose on price, context window or the category you care about most.
Last verified . 19 shared benchmarks.
CohereSummary
- They share 19 benchmarks with published results for both. Command R+ scores higher in 2 categories and gpt-oss-20b in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-20b leads 39.4 to 28.9.
- The biggest single-benchmark swing is DTBench: 54.9% for Command R+ and 68% 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 R+.
- gpt-oss-20b accepts more context: 131K tokens versus 128K.
Side by side
| Command R+ | gpt-oss-20b | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 32.4 | 32.5 |
| Released | 2024-08-30 | 2025-08-05 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 4K | 16K |
| Input $ / M tokens | $2.50 | $0.018 |
| Output $ / M tokens | $10 | $0.09 |
| Results tracked | 34 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-20b leads
Command R+: 29.1 (#309), gpt-oss-20b: 37.6 (#192)
| Benchmark | Command R+ | gpt-oss-20b |
|---|---|---|
| LMArena Coding | 1187 | 1306 |
| SciCode | — | 34.4% |
| WeirdML | — | 40.9% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| ALE-Bench | — | 566.05 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, gpt-oss-20b: 9.3 (#154)
| Benchmark | Command R+ | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |
Reasoning gpt-oss-20b leads
Command R+: 9.2 (#344), gpt-oss-20b: 19.3 (#261)
| Benchmark | Command R+ | gpt-oss-20b |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1274 |
| DTBench | 54.9% | 68% |
| LMCA | 5% | 14.5% |
| Epoch Capabilities Index | 119.34 | 137.82 |
| SimpleBench | 17.4% | — |
| Kagi LLM Benchmark | — | 53.2% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 4% |
| LiveBench Reasoning | 24.8% | — |
| LiveBench Data Analysis | 38.1% | — |
| LiveBench | 31.8% | — |
Math gpt-oss-20b leads
Command R+: 28.9 (#242), gpt-oss-20b: 39.4 (#103)
| Benchmark | Command R+ | gpt-oss-20b |
|---|---|---|
| LMArena Math | 1188 | 1317 |
| OTIS Mock AIME 2024-2025 | — | 65.3% |
| Omni-MATH | — | 56.5% |
| LiveBench Math | 21.3% | — |
Knowledge Command R+ leads
Command R+: 36.4 (#169), gpt-oss-20b: 34.6 (#195)
| Benchmark | Command R+ | gpt-oss-20b |
|---|---|---|
| LMArena Expert | 1174 | 1258 |
| GPQA Diamond | — | 60.8% |
| MMLU-Pro | — | 74% |
| Vectara Hallucination Rate | 6.9% | — |
| GPQA (HELM) | — | 59.4% |
| MMLU | 69.4% | — |
Multilingual gpt-oss-20b leads
Command R+: 38.6 (#227), gpt-oss-20b: 42.2 (#197)
| Benchmark | Command R+ | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 1216 | 1268 |
| LMArena Chinese | 1226 | 1314 |
| LMArena German | 1216 | 1255 |
| LMArena Japanese | 1166 | 1244 |
| LMArena Korean | 1138 | 1236 |
| LMArena Russian | 1227 | 1278 |
| LMArena Spanish | 1189 | 1267 |
| LMArena French | 1209 | — |
Instruction Following gpt-oss-20b leads
Command R+: 60.0 (#254), gpt-oss-20b: 61.8 (#240)
| Benchmark | Command R+ | gpt-oss-20b |
|---|---|---|
| LMArena Instruction Following | 1197 | 1236 |
| LiveBench Instruction Following | 57.6% | — |
| IFEval | — | 73.2% |
Long Context Too close to call
Command R+: 37.3 (#219), gpt-oss-20b: 37.9 (#209)
| Benchmark | Command R+ | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 1230 | 1250 |
Writing & Preference Command R+ leads
Command R+: 43.5 (#228), gpt-oss-20b: 35.5 (#265)
| Benchmark | Command R+ | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1229 | 1287 |
| LMArena Creative Writing | 1235 | 1201 |
| LMArena Multi-Turn | 1213 | 1268 |
| EQ-Bench Creative Writing | — | 666 |
| WildBench | — | 73.7% |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than gpt-oss-20b?
Command R+ and gpt-oss-20b score almost the same on the Noometry Index (32.4 vs 32.5), so choose on price, context window or the category you care about most.
Which is cheaper, Command R+ 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 R+ lists at $2.50 and $10.
Is Command R+ or gpt-oss-20b better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
gpt-oss-20b does, with 131K tokens against 128K.
How many benchmarks do Command R+ and gpt-oss-20b share?
19 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and gpt-oss-20b has 34.