Model comparison
Command R+ vs o3-mini
o3-mini is the stronger model overall, scoring 36.7 to 32.4 on the Noometry Index.
Last verified . 28 shared benchmarks.
CohereSummary
- They share 28 benchmarks with published results for both. Command R+ scores higher in 2 categories and o3-mini in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where o3-mini leads 75.1 to 60.0.
- The biggest single-benchmark swing is LiveBench Reasoning: 24.8% for Command R+ and 89.6% for o3-mini.
- o3-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $2.50 / $10 for Command R+.
- o3-mini accepts more context: 200K tokens versus 128K.
- Command R+ has downloadable open weights; the other is API-only.
Side by side
| Command R+ | o3-mini | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 32.4 | 36.7 |
| Released | 2024-08-30 | 2024-12-20 |
| 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 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Command R+: 29.1 (#309), o3-mini: 40.8 (#132)
| Benchmark | Command R+ | o3-mini |
|---|---|---|
| LiveBench Coding | 19.1% | 82.7% |
| LMArena Coding | 1187 | 1378 |
| Aider Polyglot | — | 60.4% |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| WeirdML | — | 43.7% |
| BigCodeBench Instruct | 33.8% | — |
| BigCodeBench Complete | 41.9% | — |
| CadEval | — | 54% |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, o3-mini: 29.6 (#84)
| Benchmark | Command R+ | o3-mini |
|---|---|---|
| Cybench | — | 22.5% |
Reasoning o3-mini leads
Command R+: 9.2 (#344), o3-mini: 16.3 (#305)
| Benchmark | Command R+ | o3-mini |
|---|---|---|
| SimpleBench | 17.4% | 22.8% |
| LiveBench Reasoning | 24.8% | 89.6% |
| LMArena Hard Prompts | 1186 | 1366 |
| DTBench | 54.9% | 68.8% |
| LiveBench Data Analysis | 38.1% | 70.6% |
| LMCA | 5% | 19% |
| Epoch Capabilities Index | 119.34 | 140.34 |
| LiveBench | 31.8% | 75.9% |
| ARC-AGI-2 | — | 3% |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 17% |
| Mystery Game Puzzles | — | 7% |
| ForecastBench | — | 59.6 |
Math Too close to call
Command R+: 28.9 (#242), o3-mini: 28.1 (#244)
| Benchmark | Command R+ | o3-mini |
|---|---|---|
| LiveBench Math | 21.3% | 77.3% |
| LMArena Math | 1188 | 1396 |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 76.9% |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge o3-mini leads
Command R+: 36.4 (#169), o3-mini: 38.3 (#146)
| Benchmark | Command R+ | o3-mini |
|---|---|---|
| LMArena Expert | 1174 | 1364 |
| GPQA Diamond | — | 77% |
| SimpleQA Verified | — | 15.3% |
| Confabulations | — | 17.9% |
| Vectara Hallucination Rate | 6.9% | — |
| MMLU | 69.4% | — |
Multilingual o3-mini leads
Command R+: 38.6 (#227), o3-mini: 45.7 (#164)
| Benchmark | Command R+ | o3-mini |
|---|---|---|
| LMArena Non-English | 1216 | 1319 |
| LMArena Chinese | 1226 | 1379 |
| LMArena French | 1209 | 1334 |
| LMArena German | 1216 | 1303 |
| LMArena Japanese | 1166 | 1286 |
| LMArena Korean | 1138 | 1314 |
| LMArena Russian | 1227 | 1304 |
| LMArena Spanish | 1189 | 1321 |
Instruction Following o3-mini leads
Command R+: 60.0 (#254), o3-mini: 75.1 (#72)
| Benchmark | Command R+ | o3-mini |
|---|---|---|
| LiveBench Instruction Following | 57.6% | 84.4% |
| LMArena Instruction Following | 1197 | 1337 |
Long Context Command R+ leads
Command R+: 37.3 (#219), o3-mini: 33.8 (#256)
| Benchmark | Command R+ | o3-mini |
|---|---|---|
| LMArena Longer Query | 1230 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference o3-mini leads
Command R+: 43.5 (#228), o3-mini: 50.3 (#182)
| Benchmark | Command R+ | o3-mini |
|---|---|---|
| LMArena Text | 1229 | 1337 |
| LMArena Creative Writing | 1235 | 1286 |
| LMArena Multi-Turn | 1213 | 1320 |
| LiveBench Language | 29.7% | 50.7% |
| Short-Story Creative Writing | — | 61.7% |
Frequently asked questions
Is Command R+ better than o3-mini?
o3-mini is the stronger model overall, scoring 36.7 to 32.4 on the Noometry Index.
Which is cheaper, Command R+ or o3-mini?
o3-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 o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
o3-mini does, with 200K tokens against 128K.
How many benchmarks do Command R+ and o3-mini share?
28 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and o3-mini has 51.