Model comparison
Command R+ vs gpt-oss-120b
gpt-oss-120b is the stronger model overall, scoring 36.3 to 32.4 on the Noometry Index.
Last verified . 22 shared benchmarks.
CohereSummary
- They share 22 benchmarks with published results for both. Command R+ scores higher in 1 category and gpt-oss-120b in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 28.9.
- The biggest single-benchmark swing is DTBench: 54.9% for Command R+ and 76.3% for gpt-oss-120b.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $2.50 / $10 for Command R+.
- gpt-oss-120b accepts more context: 131K tokens versus 128K.
Side by side
| Command R+ | gpt-oss-120b | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 32.4 | 36.3 |
| Released | 2024-08-30 | 2025-08-05 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 4K | 41K |
| Input $ / M tokens | $2.50 | $0.037 |
| Output $ / M tokens | $10 | $0.17 |
| Results tracked | 34 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-120b leads
Command R+: 29.1 (#309), gpt-oss-120b: 33.5 (#256)
| Benchmark | Command R+ | gpt-oss-120b |
|---|---|---|
| LMArena Coding | 1187 | 1380 |
| SWE-bench Verified (bash only) | — | 26% |
| Aider Polyglot | — | 41.8% |
| SciCode | — | 36% |
| WeirdML | — | 48.2% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| ALE-Bench | — | 575.62 |
| AlgoTune | — | 1.41 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, gpt-oss-120b: 12.2 (#153)
| Benchmark | Command R+ | gpt-oss-120b |
|---|---|---|
| Terminal-Bench | — | 18.7% |
| APEX-Agents | — | 4.4% |
| METR Time Horizons | — | 56.6% |
| Vending-Bench 2 | — | -21.53 |
Reasoning gpt-oss-120b leads
Command R+: 9.2 (#344), gpt-oss-120b: 20.0 (#245)
| Benchmark | Command R+ | gpt-oss-120b |
|---|---|---|
| SimpleBench | 17.4% | 22.1% |
| LMArena Hard Prompts | 1186 | 1364 |
| DTBench | 54.9% | 76.3% |
| LMCA | 5% | 22.1% |
| Epoch Capabilities Index | 119.34 | 139.93 |
| Kagi LLM Benchmark | — | 58.6% |
| CritPt | — | 1.1% |
| Chess Puzzles | — | 20% |
| LiveBench Reasoning | 24.8% | — |
| Mystery Game Puzzles | — | 2% |
| LiveBench Data Analysis | 38.1% | — |
| Surface Evolver Bench | — | 25% |
| LiveBench | 31.8% | — |
Math gpt-oss-120b leads
Command R+: 28.9 (#242), gpt-oss-120b: 52.5 (#50)
| Benchmark | Command R+ | gpt-oss-120b |
|---|---|---|
| LMArena Math | 1188 | 1389 |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| Omni-MATH | — | 68.8% |
| LiveBench Math | 21.3% | — |
Knowledge gpt-oss-120b leads
Command R+: 36.4 (#169), gpt-oss-120b: 42.4 (#96)
| Benchmark | Command R+ | gpt-oss-120b |
|---|---|---|
| Vectara Hallucination Rate | 6.9% | 14.2% |
| LMArena Expert | 1174 | 1356 |
| GPQA Diamond | — | 75.8% |
| MMLU-Pro | — | 79.5% |
| Confabulations | — | 15.7% |
| GPQA (HELM) | — | 68.4% |
| MMLU | 69.4% | — |
Multilingual gpt-oss-120b leads
Command R+: 38.6 (#227), gpt-oss-120b: 48.0 (#147)
| Benchmark | Command R+ | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1216 | 1351 |
| LMArena Chinese | 1226 | 1385 |
| LMArena French | 1209 | 1369 |
| LMArena German | 1216 | 1353 |
| LMArena Japanese | 1166 | 1331 |
| LMArena Korean | 1138 | 1282 |
| LMArena Russian | 1227 | 1343 |
| LMArena Spanish | 1189 | 1389 |
Instruction Following gpt-oss-120b leads
Command R+: 60.0 (#254), gpt-oss-120b: 69.3 (#173)
| Benchmark | Command R+ | gpt-oss-120b |
|---|---|---|
| LMArena Instruction Following | 1197 | 1318 |
| LiveBench Instruction Following | 57.6% | — |
| IFEval | — | 83.6% |
Long Context Command R+ leads
Command R+: 37.3 (#219), gpt-oss-120b: 31.4 (#278)
| Benchmark | Command R+ | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1230 | 1319 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference gpt-oss-120b leads
Command R+: 43.5 (#228), gpt-oss-120b: 46.5 (#217)
| Benchmark | Command R+ | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1229 | 1365 |
| LMArena Creative Writing | 1235 | 1275 |
| LMArena Multi-Turn | 1213 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| EQ-Bench Creative Writing | — | 961 |
| WildBench | — | 84.5% |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than gpt-oss-120b?
gpt-oss-120b is the stronger model overall, scoring 36.3 to 32.4 on the Noometry Index.
Which is cheaper, Command R+ or gpt-oss-120b?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or gpt-oss-120b better for coding?
gpt-oss-120b scores higher on coding benchmarks: 33.5 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
gpt-oss-120b does, with 131K tokens against 128K.
How many benchmarks do Command R+ and gpt-oss-120b share?
22 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and gpt-oss-120b has 48.