Model comparison
Command R vs GPT-4o
Command R is the stronger model overall, scoring 31.4 to 28.6 on the Noometry Index.
Last verified . 29 shared benchmarks.
CohereSummary
- They share 29 benchmarks with published results for both. Command R scores higher in 4 categories and GPT-4o in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Command R leads 28.0 to 10.6.
- The biggest single-benchmark swing is LiveBench Reasoning: 21.9% for Command R and 55.8% for GPT-4o.
- Command R is cheaper at $0.15 / $0.60 per million input/output tokens, against $2.50 / $10 for GPT-4o.
- Command R has downloadable open weights; the other is API-only.
Side by side
| Command R | GPT-4o | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 31.4 | 28.6 |
| Released | 2024-08-30 | 2024-05-13 |
| Weights | Open | Proprietary |
| Context window | 128K | 128K |
| Max output | 4K | 16K |
| Input $ / M tokens | $0.15 | $2.50 |
| Output $ / M tokens | $0.60 | $10 |
| Results tracked | 29 | 72 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Command R leads
Command R: 29.3 (#306), GPT-4o: 24.8 (#328)
| Benchmark | Command R | GPT-4o |
|---|---|---|
| BigCodeBench Instruct | 37.1% | 51.1% |
| LiveBench Coding | 17.9% | 51.4% |
| LMArena Coding | 1169 | 1297 |
| BigCodeBench Complete | 45.2% | 61.1% |
| SWE-bench Verified | — | 31% |
| SWE-bench Verified (bash only) | — | 21.6% |
| Aider Polyglot | — | 45.3% |
| GSO | — | 0% |
| WeirdML | — | 25.1% |
| CadEval | — | 26% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 72.2% |
Agentic & Tool Use Not comparable
Command R: —, GPT-4o: 21.0 (#141)
| Benchmark | Command R | GPT-4o |
|---|---|---|
| GDPval | — | 9.9% |
| TheAgentCompany | — | 8.6% |
| Cybench | — | 12.5% |
| BALROG | — | 32.3% |
| LMArena Search | — | 1006 |
| METR Time Horizons | — | 40.8% |
Reasoning Command R leads
Command R: 13.8 (#331), GPT-4o: 9.4 (#343)
| Benchmark | Command R | GPT-4o |
|---|---|---|
| LiveBench Reasoning | 21.9% | 55.8% |
| LMArena Hard Prompts | 1164 | 1281 |
| DTBench | 46.4% | 64.5% |
| LiveBench Data Analysis | 33.3% | 60.9% |
| LMCA | 9.2% | 16.6% |
| LiveBench | 27.5% | 55.3% |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 17.8% |
| ARC-AGI-1 | — | 4.5% |
| CritPt | — | 0% |
| Chess Puzzles | — | 13% |
| EnigmaEval | — | 0.8% |
| Epoch Capabilities Index | — | 128.97 |
| ForecastBench | — | 57.7 |
Math Command R leads
Command R: 28.0 (#246), GPT-4o: 10.6 (#312)
| Benchmark | Command R | GPT-4o |
|---|---|---|
| LiveBench Math | 19.4% | 49.5% |
| LMArena Math | 1155 | 1285 |
| FrontierMath (Tiers 1-3) | — | 0.4% |
| OTIS Mock AIME 2024-2025 | — | 6.4% |
| Omni-MATH | — | 29.3% |
| MATH Level 5 | — | 53.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Command R leads
Command R: 31.0 (#221), GPT-4o: 28.8 (#242)
| Benchmark | Command R | GPT-4o |
|---|---|---|
| LMArena Expert | 1138 | 1250 |
| MMLU | 65.2% | 88.1% |
| GPQA Diamond | — | 49.2% |
| Humanity's Last Exam | — | 2.7% |
| SimpleQA Verified | — | 26% |
| MMLU-Pro | — | 71.3% |
| Confabulations | — | 15.3% |
| Vectara Hallucination Rate | — | 9.6% |
| GPQA (HELM) | — | 52% |
Multimodal Not comparable
Command R: —, GPT-4o: 34.5 (#91)
| Benchmark | Command R | GPT-4o |
|---|---|---|
| LMArena Vision | — | 1137 |
| Video-MME | — | 71.9% |
| GeoBench | — | 71% |
| VPCT | — | 40% |
| ScienceQA | — | 88.5% |
Multilingual GPT-4o leads
Command R: 35.7 (#245), GPT-4o: 43.2 (#186)
| Benchmark | Command R | GPT-4o |
|---|---|---|
| LMArena Non-English | 1174 | 1283 |
| LMArena Chinese | 1182 | 1277 |
| LMArena French | 1162 | 1304 |
| LMArena German | 1176 | 1282 |
| LMArena Japanese | 1143 | 1257 |
| LMArena Korean | 1163 | 1234 |
| LMArena Russian | 1174 | 1286 |
| LMArena Spanish | 1151 | 1292 |
Instruction Following GPT-4o leads
Command R: 58.1 (#261), GPT-4o: 66.6 (#207)
| Benchmark | Command R | GPT-4o |
|---|---|---|
| LiveBench Instruction Following | 55.6% | 68.6% |
| LMArena Instruction Following | 1167 | 1278 |
| IFEval | — | 81.7% |
Long Context GPT-4o leads
Command R: 36.3 (#231), GPT-4o: 39.4 (#179)
| Benchmark | Command R | GPT-4o |
|---|---|---|
| LMArena Longer Query | 1198 | 1289 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference GPT-4o leads
Command R: 38.2 (#254), GPT-4o: 52.6 (#166)
| Benchmark | Command R | GPT-4o |
|---|---|---|
| LMArena Text | 1187 | 1300 |
| LMArena Creative Writing | 1170 | 1292 |
| LMArena Multi-Turn | 1163 | 1302 |
| LiveBench Language | 16.7% | 47.6% |
| Short-Story Creative Writing | — | 81.8% |
| WildBench | — | 82.8% |
Frequently asked questions
Is Command R better than GPT-4o?
Command R is the stronger model overall, scoring 31.4 to 28.6 on the Noometry Index.
Which is cheaper, Command R or GPT-4o?
Command R is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GPT-4o lists at $2.50 and $10.
Is Command R or GPT-4o better for coding?
Command R scores higher on coding benchmarks: 29.3 versus 24.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Command R and GPT-4o share?
29 benchmarks have published results for both models. Command R has 29 scored results on Noometry and GPT-4o has 72.