Model comparison
Command R+ vs GPT-5.1
GPT-5.1 is the stronger model overall, scoring 49.0 to 32.4 on the Noometry Index.
Last verified . 29 shared benchmarks.
CohereSummary
- They share 29 benchmarks with published results for both. Command R+ scores higher in 0 categories and GPT-5.1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.1 leads 39.8 to 9.2.
- The biggest single-benchmark swing is LiveBench Math: 21.3% for Command R+ and 94.5% for GPT-5.1.
- GPT-5.1 is cheaper at $1.25 / $10 per million input/output tokens, against $2.50 / $10 for Command R+.
- GPT-5.1 accepts more context: 400K tokens versus 128K.
- Command R+ has downloadable open weights; the other is API-only.
Side by side
| Command R+ | GPT-5.1 | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 32.4 | 49.0 |
| Released | 2024-08-30 | 2025-11-13 |
| 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 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
Command R+: 29.1 (#309), GPT-5.1: 46.4 (#66)
| Benchmark | Command R+ | GPT-5.1 |
|---|---|---|
| LiveBench Coding | 19.1% | 72.5% |
| LMArena Coding | 1187 | 1454 |
| SWE-bench Verified | — | 68% |
| SWE-bench Verified (bash only) | — | 66% |
| LMArena WebDev | — | 1395 |
| SciCode | — | 43.3% |
| GSO | — | 13.7% |
| WeirdML | — | 60.8% |
| BigCodeBench Instruct | 33.8% | — |
| BigCodeBench Complete | 41.9% | — |
| ALE-Bench | — | 1,192 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, GPT-5.1: 32.7 (#60)
| Benchmark | Command R+ | GPT-5.1 |
|---|---|---|
| Terminal-Bench | — | 47.6% |
| DeepResearch Bench | — | 42.8% |
| LMArena Search | — | 1199 |
| Vending-Bench 2 | — | 1,473 |
Reasoning GPT-5.1 leads
Command R+: 9.2 (#344), GPT-5.1: 39.8 (#58)
| Benchmark | Command R+ | GPT-5.1 |
|---|---|---|
| SimpleBench | 17.4% | 53.2% |
| LiveBench Reasoning | 24.8% | 95.8% |
| LMArena Hard Prompts | 1186 | 1457 |
| DTBench | 54.9% | 90.1% |
| LiveBench Data Analysis | 38.1% | 72.1% |
| LMCA | 5% | 43.9% |
| Epoch Capabilities Index | 119.34 | 149.64 |
| LiveBench | 31.8% | 78.8% |
| ARC-AGI-2 | — | 17.6% |
| ARC-AGI-1 | — | 72.8% |
| CritPt | — | 4.9% |
| Chess Puzzles | — | 32% |
| EnigmaEval | — | 11.2% |
| Mystery Game Puzzles | — | 19% |
| ForecastBench | — | 58.1 |
Math GPT-5.1 leads
Command R+: 28.9 (#242), GPT-5.1: 52.2 (#51)
| Benchmark | Command R+ | GPT-5.1 |
|---|---|---|
| LiveBench Math | 21.3% | 94.5% |
| LMArena Math | 1188 | 1447 |
| OTIS Mock AIME 2024-2025 | — | 88.6% |
| Omni-MATH | — | 46.4% |
| FrontierMath (Feb 2025 set) | — | 31% |
| FrontierMath Tier 4 (v1) | — | 12.5% |
Knowledge GPT-5.1 leads
Command R+: 36.4 (#169), GPT-5.1: 50.6 (#71)
| Benchmark | Command R+ | GPT-5.1 |
|---|---|---|
| Vectara Hallucination Rate | 6.9% | 10.9% |
| LMArena Expert | 1174 | 1470 |
| GPQA Diamond | — | 87.6% |
| Humanity's Last Exam | — | 23.7% |
| SimpleQA Verified | — | 48% |
| MMLU-Pro | — | 57.9% |
| GPQA (HELM) | — | 44.2% |
| MMLU | 69.4% | — |
Multimodal Not comparable
Command R+: —, GPT-5.1: 44.8 (#19)
| Benchmark | Command R+ | GPT-5.1 |
|---|---|---|
| LMArena Vision | — | 1250 |
| VPCT | — | 58.7% |
| LMArena Document | — | 1403 |
Multilingual GPT-5.1 leads
Command R+: 38.6 (#227), GPT-5.1: 53.8 (#56)
| Benchmark | Command R+ | GPT-5.1 |
|---|---|---|
| LMArena Non-English | 1216 | 1431 |
| LMArena Chinese | 1226 | 1495 |
| LMArena French | 1209 | 1450 |
| LMArena German | 1216 | 1438 |
| LMArena Japanese | 1166 | 1453 |
| LMArena Korean | 1138 | 1401 |
| LMArena Russian | 1227 | 1435 |
| LMArena Spanish | 1189 | 1433 |
Instruction Following GPT-5.1 leads
Command R+: 60.0 (#254), GPT-5.1: 83.9 (#1)
| Benchmark | Command R+ | GPT-5.1 |
|---|---|---|
| LiveBench Instruction Following | 57.6% | 93.3% |
| LMArena Instruction Following | 1197 | 1443 |
| IFEval | — | 93.5% |
Long Context GPT-5.1 leads
Command R+: 37.3 (#219), GPT-5.1: 47.6 (#14)
| Benchmark | Command R+ | GPT-5.1 |
|---|---|---|
| LMArena Longer Query | 1230 | 1447 |
| CL-bench | — | 23.7% |
| CL-bench Life | — | 17.3% |
Writing & Preference GPT-5.1 leads
Command R+: 43.5 (#228), GPT-5.1: 64.5 (#55)
| Benchmark | Command R+ | GPT-5.1 |
|---|---|---|
| LMArena Text | 1229 | 1443 |
| LMArena Creative Writing | 1235 | 1427 |
| LMArena Multi-Turn | 1213 | 1450 |
| LiveBench Language | 29.7% | 80.2% |
| WildBench | — | 86.3% |
Frequently asked questions
Is Command R+ better than GPT-5.1?
GPT-5.1 is the stronger model overall, scoring 49.0 to 32.4 on the Noometry Index.
Which is cheaper, Command R+ or GPT-5.1?
GPT-5.1 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-5.1 better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.4 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5.1 does, with 400K tokens against 128K.
How many benchmarks do Command R+ and GPT-5.1 share?
29 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and GPT-5.1 has 63.