Model comparison
Command R+ vs GPT-4 Turbo
Command R+ is the stronger model overall, scoring 32.4 to 30.5 on the Noometry Index.
Last verified . 26 shared benchmarks.
CohereSummary
- They share 26 benchmarks with published results for both. Command R+ scores higher in 2 categories and GPT-4 Turbo in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Command R+ leads 28.9 to 9.0.
- The biggest single-benchmark swing is BigCodeBench Complete: 41.9% for Command R+ and 58.2% for GPT-4 Turbo.
- Command R+ is cheaper at $2.50 / $10 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- Command R+ has downloadable open weights; the other is API-only.
Side by side
| Command R+ | GPT-4 Turbo | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 32.4 | 30.5 |
| Released | 2024-08-30 | 2023-11-06 |
| Weights | Open | Proprietary |
| Context window | 128K | 128K |
| Max output | 4K | 4K |
| Input $ / M tokens | $2.50 | $10 |
| Output $ / M tokens | $10 | $30 |
| Results tracked | 34 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4 Turbo leads
Command R+: 29.1 (#309), GPT-4 Turbo: 33.8 (#249)
| Benchmark | Command R+ | GPT-4 Turbo |
|---|---|---|
| BigCodeBench Instruct | 33.8% | 48.2% |
| LMArena Coding | 1187 | 1268 |
| BigCodeBench Complete | 41.9% | 58.2% |
| HumanEval+ | 56.7% | 86.6% |
| MBPP+ | 63.5% | 73.3% |
| WeirdML | — | 18% |
| LiveBench Coding | 19.1% | — |
Agentic & Tool Use Not comparable
Command R+: —, GPT-4 Turbo: —
| Benchmark | Command R+ | GPT-4 Turbo |
|---|---|---|
| METR Time Horizons | — | 36.7% |
Reasoning GPT-4 Turbo leads
Command R+: 9.2 (#344), GPT-4 Turbo: 15.3 (#317)
| Benchmark | Command R+ | GPT-4 Turbo |
|---|---|---|
| SimpleBench | 17.4% | 25.1% |
| LMArena Hard Prompts | 1186 | 1251 |
| DTBench | 54.9% | 61.6% |
| LMCA | 5% | 9.8% |
| Epoch Capabilities Index | 119.34 | 127.25 |
| Chess Puzzles | — | 6% |
| LiveBench Reasoning | 24.8% | — |
| LiveBench Data Analysis | 38.1% | — |
| ForecastBench | — | 59.4 |
| LiveBench | 31.8% | — |
Math Command R+ leads
Command R+: 28.9 (#242), GPT-4 Turbo: 9.0 (#322)
| Benchmark | Command R+ | GPT-4 Turbo |
|---|---|---|
| LMArena Math | 1188 | 1272 |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| OTIS Mock AIME 2024-2025 | — | 6.7% |
| LiveBench Math | 21.3% | — |
| MATH Level 5 | — | 46.7% |
Knowledge Command R+ leads
Command R+: 36.4 (#169), GPT-4 Turbo: 24.3 (#268)
| Benchmark | Command R+ | GPT-4 Turbo |
|---|---|---|
| LMArena Expert | 1174 | 1223 |
| MMLU | 69.4% | 81.3% |
| GPQA Diamond | — | 46.6% |
| Confabulations | — | 28.4% |
| Vectara Hallucination Rate | 6.9% | — |
Multimodal Not comparable
Command R+: —, GPT-4 Turbo: 30.6 (#110)
| Benchmark | Command R+ | GPT-4 Turbo |
|---|---|---|
| LMArena Vision | — | 1090 |
Multilingual GPT-4 Turbo leads
Command R+: 38.6 (#227), GPT-4 Turbo: 40.5 (#216)
| Benchmark | Command R+ | GPT-4 Turbo |
|---|---|---|
| LMArena Non-English | 1216 | 1245 |
| LMArena Chinese | 1226 | 1242 |
| LMArena French | 1209 | 1276 |
| LMArena German | 1216 | 1259 |
| LMArena Japanese | 1166 | 1194 |
| LMArena Korean | 1138 | 1187 |
| LMArena Russian | 1227 | 1259 |
| LMArena Spanish | 1189 | 1260 |
Instruction Following GPT-4 Turbo leads
Command R+: 60.0 (#254), GPT-4 Turbo: 65.8 (#216)
| Benchmark | Command R+ | GPT-4 Turbo |
|---|---|---|
| LMArena Instruction Following | 1197 | 1249 |
| LiveBench Instruction Following | 57.6% | — |
Long Context Too close to call
Command R+: 37.3 (#219), GPT-4 Turbo: 38.0 (#206)
| Benchmark | Command R+ | GPT-4 Turbo |
|---|---|---|
| LMArena Longer Query | 1230 | 1254 |
Writing & Preference GPT-4 Turbo leads
Command R+: 43.5 (#228), GPT-4 Turbo: 47.7 (#206)
| Benchmark | Command R+ | GPT-4 Turbo |
|---|---|---|
| LMArena Text | 1229 | 1272 |
| LMArena Creative Writing | 1235 | 1269 |
| LMArena Multi-Turn | 1213 | 1267 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than GPT-4 Turbo?
Command R+ is the stronger model overall, scoring 32.4 to 30.5 on the Noometry Index.
Which is cheaper, Command R+ or GPT-4 Turbo?
Command R+ is cheaper. It lists at $2.50 per million input tokens and $10 per million output tokens; GPT-4 Turbo lists at $10 and $30.
Is Command R+ or GPT-4 Turbo better for coding?
GPT-4 Turbo scores higher on coding benchmarks: 33.8 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Command R+ and GPT-4 Turbo share?
26 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and GPT-4 Turbo has 36.