Model comparison
Command R+ vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 61.8 to 32.4 on the Noometry Index.
Last verified . 21 shared benchmarks.
CohereSummary
- They share 21 benchmarks with published results for both. Command R+ scores higher in 0 categories and GPT-6 Sol in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 74.0 to 9.2.
- The biggest single-benchmark swing is LMCA: 5% for Command R+ and 59.1% for GPT-6 Sol.
- GPT-6 Sol is cheaper at $2 / $10 per million input/output tokens, against $2.50 / $10 for Command R+.
- GPT-6 Sol accepts more context: 1.05M tokens versus 128K.
- Command R+ has downloadable open weights; the other is API-only.
Side by side
| Command R+ | GPT-6 Sol | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 32.4 | 61.8 |
| Released | 2024-08-30 | 2026-09-22 |
| Weights | Open | Proprietary |
| Context window | 128K | 1.05M |
| Max output | 4K | 128K |
| Input $ / M tokens | $2.50 | $2 |
| Output $ / M tokens | $10 | $10 |
| Results tracked | 34 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
Command R+: 29.1 (#309), GPT-6 Sol: 60.1 (#11)
| Benchmark | Command R+ | GPT-6 Sol |
|---|---|---|
| LMArena Coding | 1187 | 1447 |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| LMArena WebDev | — | 1688 |
| SciCode | — | 57.6% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| ALE-Bench | — | 2,462 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, GPT-6 Sol: 37.2 (#36)
| Benchmark | Command R+ | GPT-6 Sol |
|---|---|---|
| APEX-Agents | — | 54.3% |
| GDP.pdf | — | 26.4% |
| Vending-Bench 2 | — | 14,428 |
Reasoning GPT-6 Sol leads
Command R+: 9.2 (#344), GPT-6 Sol: 74.0 (#9)
| Benchmark | Command R+ | GPT-6 Sol |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1418 |
| DTBench | 54.9% | 97.3% |
| LMCA | 5% | 59.1% |
| Epoch Capabilities Index | 119.34 | 162.72 |
| ARC-AGI-2 | — | 89.6% |
| SimpleBench | 17.4% | — |
| NYT Connections (extended) | — | 90.1% |
| ARC-AGI-1 | — | 95.5% |
| CritPt | — | 30.9% |
| EBR-Bench | — | 53.3% |
| LiveBench Reasoning | 24.8% | — |
| Mystery Game Puzzles | — | 56% |
| LiveBench Data Analysis | 38.1% | — |
| LiveBench | 31.8% | — |
Math GPT-6 Sol leads
Command R+: 28.9 (#242), GPT-6 Sol: 87.2 (#7)
| Benchmark | Command R+ | GPT-6 Sol |
|---|---|---|
| LMArena Math | 1188 | 1402 |
| FrontierMath (Tiers 1-3) | — | 89.8% |
| FrontierMath Tier 4 | — | 90% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 83% |
| LiveBench Math | 21.3% | — |
Knowledge GPT-6 Sol leads
Command R+: 36.4 (#169), GPT-6 Sol: 64.8 (#15)
| Benchmark | Command R+ | GPT-6 Sol |
|---|---|---|
| Vectara Hallucination Rate | 6.9% | 6.5% |
| LMArena Expert | 1174 | 1439 |
| GPQA Diamond | — | 94.3% |
| SimpleQA Verified | — | 60.7% |
| MMLU | 69.4% | — |
Multimodal Not comparable
Command R+: —, GPT-6 Sol: 47.6 (#10)
| Benchmark | Command R+ | GPT-6 Sol |
|---|---|---|
| LMArena Vision | — | 1245 |
| Blueprint-Bench 2 | — | 36.9% |
| Furniture Assembly | — | 58.3% |
Multilingual GPT-6 Sol leads
Command R+: 38.6 (#227), GPT-6 Sol: 50.5 (#118)
| Benchmark | Command R+ | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1216 | 1385 |
| LMArena Chinese | 1226 | 1405 |
| LMArena French | 1209 | 1410 |
| LMArena German | 1216 | 1390 |
| LMArena Japanese | 1166 | 1385 |
| LMArena Korean | 1138 | 1341 |
| LMArena Russian | 1227 | 1401 |
| LMArena Spanish | 1189 | 1384 |
Instruction Following GPT-6 Sol leads
Command R+: 60.0 (#254), GPT-6 Sol: 74.5 (#94)
| Benchmark | Command R+ | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1197 | 1412 |
| LiveBench Instruction Following | 57.6% | — |
Long Context GPT-6 Sol leads
Command R+: 37.3 (#219), GPT-6 Sol: 43.1 (#108)
| Benchmark | Command R+ | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1230 | 1411 |
Writing & Preference GPT-6 Sol leads
Command R+: 43.5 (#228), GPT-6 Sol: 71.9 (#18)
| Benchmark | Command R+ | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1229 | 1395 |
| LMArena Creative Writing | 1235 | 1378 |
| LMArena Multi-Turn | 1213 | 1412 |
| EQ-Bench Creative Writing | — | 2125 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 32.4 on the Noometry Index.
Which is cheaper, Command R+ or GPT-6 Sol?
GPT-6 Sol is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 128K.
How many benchmarks do Command R+ and GPT-6 Sol share?
21 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and GPT-6 Sol has 45.