Model comparison
Command R+ vs GPT-5
GPT-5 is the stronger model overall, scoring 50.9 to 32.0 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 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where GPT-5 leads 69.5 to 37.3.
- The biggest single-benchmark swing is SimpleBench: 17.4% for Command R+ and 56.7% for GPT-5.
- GPT-5 is cheaper at $1.25 / $10 per million input/output tokens, against $2.50 / $10 for Command R+.
- GPT-5 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 | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 32.0 | 50.9 |
| Released | 2024-08-30 | 2025-08-07 |
| Weights | Open | Proprietary |
| Context window | 128K | 400K |
| Max output | 4K | 128K |
| Input $ / M tokens | $2.50 | $1.25 |
| Output $ / M tokens | $10 | $10 |
| Results tracked | 34 | 69 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 leads
Command R+: 28.6 (#304), GPT-5: 50.7 (#39)
| Benchmark | Command R+ | GPT-5 |
|---|---|---|
| LMArena Coding | 1187 | 1436 |
| SWE-bench Verified | — | 73.6% |
| SWE-bench Verified (bash only) | — | 65% |
| Aider Polyglot | — | 88% |
| LMArena WebDev | — | 1417 |
| SciCode | — | 42.9% |
| GSO | — | 6.9% |
| WeirdML | — | 60.7% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| ALE-Bench | — | 1,162 |
| AlgoTune | — | 1.67 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, GPT-5: 33.0 (#53)
| Benchmark | Command R+ | GPT-5 |
|---|---|---|
| Terminal-Bench | — | 49.6% |
| GDPval | — | 34.8% |
| Remote Labor Index | — | 1.7% |
| DeepResearch Bench | — | 49.6% |
| BALROG | — | 32.8% |
| LMArena Search | — | 1133 |
| METR Time Horizons | — | 69.6% |
Reasoning GPT-5 leads
Command R+: 8.9 (#341), GPT-5: 38.3 (#55)
| Benchmark | Command R+ | GPT-5 |
|---|---|---|
| SimpleBench | 17.4% | 56.7% |
| LMArena Hard Prompts | 1186 | 1415 |
| DTBench | 54.9% | 90.7% |
| LMCA | 5% | 40% |
| Epoch Capabilities Index | 119.28 | 150 |
| ARC-AGI-2 | — | 9.9% |
| Kagi LLM Benchmark | — | 72.7% |
| ARC-AGI-1 | — | 65.7% |
| CritPt | — | 12.6% |
| Chess Puzzles | — | 37% |
| EnigmaEval | — | 10.5% |
| EBR-Bench | — | 12.7% |
| LiveBench Reasoning | 24.8% | — |
| Mystery Game Puzzles | — | 23% |
| LiveBench Data Analysis | 38.1% | — |
| ForecastBench | — | 61.4 |
| LiveBench | 31.8% | — |
Math GPT-5 leads
Command R+: 26.6 (#239), GPT-5: 54.6 (#36)
| Benchmark | Command R+ | GPT-5 |
|---|---|---|
| LMArena Math | 1188 | 1406 |
| FrontierMath (Tiers 1-3) | — | 55.4% |
| FrontierMath Tier 4 | — | 22% |
| OTIS Mock AIME 2024-2025 | — | 91.4% |
| ProofBench | — | 18% |
| Omni-MATH | — | 64.7% |
| LiveBench Math | 21.3% | — |
| MATH Level 5 | — | 98.1% |
| FrontierMath (Feb 2025 set) | — | 32.4% |
| FrontierMath Tier 4 (v1) | — | 12.5% |
Knowledge GPT-5 leads
Command R+: 35.9 (#165), GPT-5: 56.5 (#37)
| Benchmark | Command R+ | GPT-5 |
|---|---|---|
| Vectara Hallucination Rate | 6.9% | 14.7% |
| LMArena Expert | 1174 | 1420 |
| GPQA Diamond | — | 86.2% |
| Humanity's Last Exam | — | 25.3% |
| SimpleQA Verified | — | 50.1% |
| MMLU-Pro | — | 86.3% |
| Confabulations | — | 10.3% |
| GPQA (HELM) | — | 79.2% |
| MMLU | 69.4% | — |
Multimodal Not comparable
Command R+: —, GPT-5: 46.1 (#12)
| Benchmark | Command R+ | GPT-5 |
|---|---|---|
| LMArena Vision | — | 1232 |
| GeoBench | — | 81% |
| VPCT | — | 66% |
Multilingual GPT-5 leads
Command R+: 38.8 (#222), GPT-5: 51.5 (#105)
| Benchmark | Command R+ | GPT-5 |
|---|---|---|
| LMArena Non-English | 1216 | 1397 |
| LMArena Chinese | 1226 | 1423 |
| LMArena French | 1208 | 1409 |
| LMArena German | 1216 | 1415 |
| LMArena Japanese | 1166 | 1411 |
| LMArena Korean | 1138 | 1361 |
| LMArena Russian | 1227 | 1406 |
| LMArena Spanish | 1189 | 1398 |
Instruction Following GPT-5 leads
Command R+: 60.2 (#249), GPT-5: 74.0 (#107)
| Benchmark | Command R+ | GPT-5 |
|---|---|---|
| LMArena Instruction Following | 1197 | 1388 |
| LiveBench Instruction Following | 57.6% | — |
| IFEval | — | 87.5% |
Long Context GPT-5 leads
Command R+: 37.3 (#214), GPT-5: 69.5 (#2)
| Benchmark | Command R+ | GPT-5 |
|---|---|---|
| LMArena Longer Query | 1231 | 1399 |
| Fiction.LiveBench | — | 97.2% |
Writing & Preference GPT-5 leads
Command R+: 43.7 (#223), GPT-5: 63.5 (#63)
| Benchmark | Command R+ | GPT-5 |
|---|---|---|
| LMArena Text | 1229 | 1406 |
| LMArena Creative Writing | 1235 | 1365 |
| LMArena Multi-Turn | 1213 | 1426 |
| Short-Story Creative Writing | — | 86% |
| EQ-Bench Creative Writing | — | 1627 |
| WildBench | — | 85.7% |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than GPT-5?
GPT-5 is the stronger model overall, scoring 50.9 to 32.0 on the Noometry Index.
Which is cheaper, Command R+ or GPT-5?
GPT-5 is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or GPT-5 better for coding?
GPT-5 scores higher on coding benchmarks: 50.7 versus 28.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5 does, with 400K tokens against 128K.
How many benchmarks do Command R+ and GPT-5 share?
22 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and GPT-5 has 69.