Model comparison
Command R+ vs GPT-5.2
GPT-5.2 is the stronger model overall, scoring 54.1 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 0 categories and GPT-5.2 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.2 leads 50.2 to 9.2.
- The biggest single-benchmark swing is LMCA: 5% for Command R+ and 43.9% for GPT-5.2.
- Command R+ is cheaper at $2.50 / $10 per million input/output tokens, against $1.75 / $14 for GPT-5.2.
- GPT-5.2 accepts more context: 400K tokens versus 128K.
- Command R+ has downloadable open weights; the other is API-only.
Side by side
| Command R+ | GPT-5.2 | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 32.4 | 54.1 |
| Released | 2024-08-30 | 2025-12-11 |
| Weights | Open | Proprietary |
| Context window | 128K | 400K |
| Max output | 4K | 128K |
| Input $ / M tokens | $2.50 | $1.75 |
| Output $ / M tokens | $10 | $14 |
| Results tracked | 34 | 67 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.2 leads
Command R+: 29.1 (#309), GPT-5.2: 51.6 (#37)
| Benchmark | Command R+ | GPT-5.2 |
|---|---|---|
| LMArena Coding | 1187 | 1447 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 72.8% |
| LMArena WebDev | — | 1416 |
| SWE-bench Multilingual | — | 66.7% |
| GSO | — | 27.4% |
| WeirdML | — | 72.2% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| ALE-Bench | — | 1,294 |
| AlgoTune | — | 2.05 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, GPT-5.2: 40.2 (#24)
| Benchmark | Command R+ | GPT-5.2 |
|---|---|---|
| Terminal-Bench | — | 64.9% |
| Berkeley Function Calling Leaderboard | — | 55.9% |
| GDPval | — | 49.7% |
| Remote Labor Index | — | 2.5% |
| τ²-bench Airline | — | 83% |
| τ²-bench Banking | — | 32.2% |
| τ²-bench Retail | — | 81.6% |
| τ²-bench Telecom | — | 89.7% |
| DeepResearch Bench | — | 41.1% |
| LMArena Search | — | 1207 |
| METR Time Horizons | — | 75.3% |
| Vending-Bench 2 | — | 3,591 |
Reasoning GPT-5.2 leads
Command R+: 9.2 (#344), GPT-5.2: 50.2 (#35)
| Benchmark | Command R+ | GPT-5.2 |
|---|---|---|
| SimpleBench | 17.4% | 45.8% |
| LMArena Hard Prompts | 1186 | 1445 |
| DTBench | 54.9% | 90.9% |
| LMCA | 5% | 43.9% |
| Epoch Capabilities Index | 119.34 | 153.45 |
| ARC-AGI-2 | — | 52.9% |
| Kagi LLM Benchmark | — | 73.3% |
| NYT Connections (extended) | — | 83.6% |
| ARC-AGI-1 | — | 86.2% |
| Chess Puzzles | — | 49% |
| EnigmaEval | — | 10.4% |
| EBR-Bench | — | 23% |
| LiveBench Reasoning | 24.8% | — |
| Mystery Game Puzzles | — | 23% |
| LiveBench Data Analysis | 38.1% | — |
| ForecastBench | — | 60.1 |
| LiveBench | 31.8% | — |
Math GPT-5.2 leads
Command R+: 28.9 (#242), GPT-5.2: 60.0 (#38)
| Benchmark | Command R+ | GPT-5.2 |
|---|---|---|
| LMArena Math | 1188 | 1440 |
| FrontierMath (Tiers 1-3) | — | 67.4% |
| FrontierMath Tier 4 | — | 31.7% |
| MathArena Final-Answer Competitions | — | 72% |
| OTIS Mock AIME 2024-2025 | — | 96.1% |
| ProofBench | — | 15% |
| LiveBench Math | 21.3% | — |
| FrontierMath (Feb 2025 set) | — | 40.7% |
| FrontierMath Tier 4 (v1) | — | 18.8% |
Knowledge GPT-5.2 leads
Command R+: 36.4 (#169), GPT-5.2: 59.3 (#32)
| Benchmark | Command R+ | GPT-5.2 |
|---|---|---|
| Vectara Hallucination Rate | 6.9% | 8.4% |
| LMArena Expert | 1174 | 1445 |
| GPQA Diamond | — | 91.4% |
| Humanity's Last Exam | — | 27.8% |
| SimpleQA Verified | — | 37.1% |
| MMLU | 69.4% | — |
Multimodal Not comparable
Command R+: —, GPT-5.2: 51.3 (#7)
| Benchmark | Command R+ | GPT-5.2 |
|---|---|---|
| LMArena Vision | — | 1268 |
| VPCT | — | 84% |
| Furniture Assembly | — | 38.3% |
| LMArena Document | — | 1405 |
Multilingual GPT-5.2 leads
Command R+: 38.6 (#227), GPT-5.2: 53.4 (#67)
| Benchmark | Command R+ | GPT-5.2 |
|---|---|---|
| LMArena Non-English | 1216 | 1425 |
| LMArena Chinese | 1226 | 1460 |
| LMArena French | 1209 | 1455 |
| LMArena German | 1216 | 1448 |
| LMArena Japanese | 1166 | 1420 |
| LMArena Korean | 1138 | 1392 |
| LMArena Russian | 1227 | 1440 |
| LMArena Spanish | 1189 | 1433 |
Instruction Following GPT-5.2 leads
Command R+: 60.0 (#254), GPT-5.2: 74.7 (#89)
| Benchmark | Command R+ | GPT-5.2 |
|---|---|---|
| LMArena Instruction Following | 1197 | 1417 |
| LiveBench Instruction Following | 57.6% | — |
Long Context GPT-5.2 leads
Command R+: 37.3 (#219), GPT-5.2: 44.0 (#78)
| Benchmark | Command R+ | GPT-5.2 |
|---|---|---|
| LMArena Longer Query | 1230 | 1428 |
| CL-bench | — | 18.2% |
Writing & Preference GPT-5.2 leads
Command R+: 43.5 (#228), GPT-5.2: 66.8 (#32)
| Benchmark | Command R+ | GPT-5.2 |
|---|---|---|
| LMArena Text | 1229 | 1439 |
| LMArena Creative Writing | 1235 | 1401 |
| LMArena Multi-Turn | 1213 | 1458 |
| EQ-Bench Creative Writing | — | 1703 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than GPT-5.2?
GPT-5.2 is the stronger model overall, scoring 54.1 to 32.4 on the Noometry Index.
Which is cheaper, Command R+ or GPT-5.2?
Command R+ is cheaper. It lists at $2.50 per million input tokens and $10 per million output tokens; GPT-5.2 lists at $1.75 and $14.
Is Command R+ or GPT-5.2 better for coding?
GPT-5.2 scores higher on coding benchmarks: 51.6 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5.2 does, with 400K tokens against 128K.
How many benchmarks do Command R+ and GPT-5.2 share?
22 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and GPT-5.2 has 67.