Model comparison
Command R+ vs GPT-4o mini
Command R+ is the stronger model overall, scoring 32.4 to 25.5 on the Noometry Index. GPT-4o mini costs 17× less per token, which makes it the better buy when Command R+'s lead doesn't matter for your workload.
Last verified . 33 shared benchmarks.
CohereSummary
- They share 33 benchmarks with published results for both. Command R+ scores higher in 5 categories and GPT-4o mini in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Command R+ leads 36.4 to 17.7.
- The biggest single-benchmark swing is LiveBench Coding: 19.1% for Command R+ and 43.1% for GPT-4o mini.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $2.50 / $10 for Command R+.
- Command R+ has downloadable open weights; the other is API-only.
Side by side
| Command R+ | GPT-4o mini | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 32.4 | 25.5 |
| Released | 2024-08-30 | 2024-07-18 |
| Weights | Open | Proprietary |
| Context window | 128K | 128K |
| Max output | 4K | 16K |
| Input $ / M tokens | $2.50 | $0.15 |
| Output $ / M tokens | $10 | $0.60 |
| Results tracked | 34 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Command R+ leads
Command R+: 29.1 (#309), GPT-4o mini: 22.0 (#335)
| Benchmark | Command R+ | GPT-4o mini |
|---|---|---|
| BigCodeBench Instruct | 33.8% | 46.1% |
| LiveBench Coding | 19.1% | 43.1% |
| LMArena Coding | 1187 | 1290 |
| BigCodeBench Complete | 41.9% | 57.4% |
| HumanEval+ | 56.7% | 83.5% |
| MBPP+ | 63.5% | 72.2% |
| Aider Polyglot | — | 3.6% |
| WeirdML | — | 11.8% |
Agentic & Tool Use Not comparable
Command R+: —, GPT-4o mini: 27.5 (#101)
| Benchmark | Command R+ | GPT-4o mini |
|---|---|---|
| BALROG | — | 17.4% |
Reasoning Too close to call
Command R+: 9.2 (#344), GPT-4o mini: 8.7 (#347)
| Benchmark | Command R+ | GPT-4o mini |
|---|---|---|
| SimpleBench | 17.4% | 10.7% |
| LiveBench Reasoning | 24.8% | 32.8% |
| LMArena Hard Prompts | 1186 | 1267 |
| DTBench | 54.9% | 54.4% |
| LiveBench Data Analysis | 38.1% | 50% |
| LMCA | 5% | 10.4% |
| Epoch Capabilities Index | 119.34 | 126.56 |
| LiveBench | 31.8% | 41.3% |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 28.8% |
| Chess Puzzles | — | 0% |
| Mystery Game Puzzles | — | 12% |
| PIQA | — | 88.7% |
Math Command R+ leads
Command R+: 28.9 (#242), GPT-4o mini: 10.4 (#314)
| Benchmark | Command R+ | GPT-4o mini |
|---|---|---|
| LiveBench Math | 21.3% | 36.3% |
| LMArena Math | 1188 | 1267 |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| OTIS Mock AIME 2024-2025 | — | 6.9% |
| Omni-MATH | — | 28% |
| MATH Level 5 | — | 52.6% |
| GSM8K | — | 91.3% |
Knowledge Command R+ leads
Command R+: 36.4 (#169), GPT-4o mini: 17.7 (#284)
| Benchmark | Command R+ | GPT-4o mini |
|---|---|---|
| LMArena Expert | 1174 | 1235 |
| MMLU | 69.4% | 81.8% |
| GPQA Diamond | — | 37.7% |
| SimpleQA Verified | — | 8.3% |
| MMLU-Pro | — | 60.3% |
| Confabulations | — | 37.2% |
| Vectara Hallucination Rate | 6.9% | — |
| GPQA (HELM) | — | 36.8% |
| BoolQ | — | 88.7% |
Multimodal Not comparable
Command R+: —, GPT-4o mini: 25.9 (#122)
| Benchmark | Command R+ | GPT-4o mini |
|---|---|---|
| LMArena Vision | — | 1066 |
| Video-MME | — | 64.8% |
| GeoBench | — | 64% |
| VPCT | — | 34% |
Multilingual GPT-4o mini leads
Command R+: 38.6 (#227), GPT-4o mini: 42.0 (#199)
| Benchmark | Command R+ | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1216 | 1266 |
| LMArena Chinese | 1226 | 1265 |
| LMArena French | 1209 | 1297 |
| LMArena German | 1216 | 1272 |
| LMArena Japanese | 1166 | 1216 |
| LMArena Korean | 1138 | 1195 |
| LMArena Russian | 1227 | 1275 |
| LMArena Spanish | 1189 | 1276 |
Instruction Following GPT-4o mini leads
Command R+: 60.0 (#254), GPT-4o mini: 61.9 (#239)
| Benchmark | Command R+ | GPT-4o mini |
|---|---|---|
| LiveBench Instruction Following | 57.6% | 56.8% |
| LMArena Instruction Following | 1197 | 1258 |
| IFEval | — | 78.2% |
Long Context GPT-4o mini leads
Command R+: 37.3 (#219), GPT-4o mini: 39.1 (#186)
| Benchmark | Command R+ | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1230 | 1289 |
Writing & Preference Command R+ leads
Command R+: 43.5 (#228), GPT-4o mini: 39.5 (#248)
| Benchmark | Command R+ | GPT-4o mini |
|---|---|---|
| LMArena Text | 1229 | 1286 |
| LMArena Creative Writing | 1235 | 1268 |
| LMArena Multi-Turn | 1213 | 1285 |
| LiveBench Language | 29.7% | 28.6% |
| Short-Story Creative Writing | — | 67.2% |
| EQ-Bench Creative Writing | — | 873 |
| WildBench | — | 79.1% |
Frequently asked questions
Is Command R+ better than GPT-4o mini?
Command R+ is the stronger model overall, scoring 32.4 to 25.5 on the Noometry Index. GPT-4o mini costs 17× less per token, which makes it the better buy when Command R+'s lead doesn't matter for your workload.
Which is cheaper, Command R+ or GPT-4o mini?
GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or GPT-4o mini better for coding?
Command R+ scores higher on coding benchmarks: 29.1 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Command R+ and GPT-4o mini share?
33 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and GPT-4o mini has 60.