Model comparison
Command R+ vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 to 32.4 on the Noometry Index.
Last verified . 22 shared benchmarks.
CohereSummary
- They share 22 benchmarks with published results for both. Command R+ scores higher in 0 categories and o4-mini in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where o4-mini leads 24.6 to 9.2.
- The biggest single-benchmark swing is DTBench: 54.9% for Command R+ and 77.6% for o4-mini.
- o4-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $2.50 / $10 for Command R+.
- o4-mini accepts more context: 200K tokens versus 128K.
- Command R+ has downloadable open weights; the other is API-only.
Side by side
| Command R+ | o4-mini | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 32.4 | 41.6 |
| Released | 2024-08-30 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 128K | 200K |
| Max output | 4K | 100K |
| Input $ / M tokens | $2.50 | $1.10 |
| Output $ / M tokens | $10 | $4.40 |
| Results tracked | 34 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
Command R+: 29.1 (#309), o4-mini: 40.9 (#127)
| Benchmark | Command R+ | o4-mini |
|---|---|---|
| LMArena Coding | 1187 | 1368 |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| GSO | — | 3.6% |
| WeirdML | — | 52.6% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| CadEval | — | 62% |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, o4-mini: 32.6 (#61)
| Benchmark | Command R+ | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| METR Time Horizons | — | 63.9% |
Reasoning o4-mini leads
Command R+: 9.2 (#344), o4-mini: 24.6 (#162)
| Benchmark | Command R+ | o4-mini |
|---|---|---|
| SimpleBench | 17.4% | 38.7% |
| LMArena Hard Prompts | 1186 | 1351 |
| DTBench | 54.9% | 77.6% |
| LMCA | 5% | 26.5% |
| Epoch Capabilities Index | 119.34 | 145.64 |
| ARC-AGI-2 | — | 6.1% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 58.7% |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| LiveBench Reasoning | 24.8% | — |
| Mystery Game Puzzles | — | 5% |
| LiveBench Data Analysis | 38.1% | — |
| ForecastBench | — | 61.8 |
| LiveBench | 31.8% | — |
Math o4-mini leads
Command R+: 28.9 (#242), o4-mini: 40.8 (#89)
| Benchmark | Command R+ | o4-mini |
|---|---|---|
| LMArena Math | 1188 | 1389 |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 81.7% |
| Omni-MATH | — | 72% |
| LiveBench Math | 21.3% | — |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
Command R+: 36.4 (#169), o4-mini: 43.6 (#91)
| Benchmark | Command R+ | o4-mini |
|---|---|---|
| Vectara Hallucination Rate | 6.9% | 18.6% |
| LMArena Expert | 1174 | 1343 |
| GPQA Diamond | — | 79.6% |
| Humanity's Last Exam | — | 18.1% |
| SimpleQA Verified | — | 19.6% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| GPQA (HELM) | — | 73.5% |
| MMLU | 69.4% | — |
Multimodal Not comparable
Command R+: —, o4-mini: 40.2 (#49)
| Benchmark | Command R+ | o4-mini |
|---|---|---|
| LMArena Vision | — | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual o4-mini leads
Command R+: 38.6 (#227), o4-mini: 47.0 (#154)
| Benchmark | Command R+ | o4-mini |
|---|---|---|
| LMArena Non-English | 1216 | 1337 |
| LMArena Chinese | 1226 | 1354 |
| LMArena French | 1209 | 1364 |
| LMArena German | 1216 | 1336 |
| LMArena Japanese | 1166 | 1308 |
| LMArena Korean | 1138 | 1312 |
| LMArena Russian | 1227 | 1334 |
| LMArena Spanish | 1189 | 1347 |
Instruction Following o4-mini leads
Command R+: 60.0 (#254), o4-mini: 75.2 (#68)
| Benchmark | Command R+ | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1197 | 1321 |
| LiveBench Instruction Following | 57.6% | — |
| IFEval | — | 92.8% |
Long Context o4-mini leads
Command R+: 37.3 (#219), o4-mini: 45.5 (#33)
| Benchmark | Command R+ | o4-mini |
|---|---|---|
| LMArena Longer Query | 1230 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference o4-mini leads
Command R+: 43.5 (#228), o4-mini: 54.0 (#152)
| Benchmark | Command R+ | o4-mini |
|---|---|---|
| LMArena Text | 1229 | 1353 |
| LMArena Creative Writing | 1235 | 1294 |
| LMArena Multi-Turn | 1213 | 1350 |
| Short-Story Creative Writing | — | 75% |
| WildBench | — | 85.4% |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 32.4 on the Noometry Index.
Which is cheaper, Command R+ or o4-mini?
o4-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or o4-mini better for coding?
o4-mini scores higher on coding benchmarks: 40.9 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
o4-mini does, with 200K tokens against 128K.
How many benchmarks do Command R+ and o4-mini share?
22 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and o4-mini has 60.