Model comparison
Command R vs Grok-3 mini
Grok-3 mini is the stronger model overall, scoring 41.2 to 31.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
CohereSummary
- They share 17 benchmarks with published results for both. Command R scores higher in 1 category and Grok-3 mini in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Grok-3 mini leads 78.5 to 58.1.
- Command R has downloadable open weights; the other is API-only.
Side by side
| Command R | Grok-3 mini | |
|---|---|---|
| Provider | Cohere | xAI |
| Noometry Index | 31.4 | 41.2 |
| Released | 2024-08-30 | 2025-04-09 |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 29 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Command R: 29.3 (#306), Grok-3 mini: 40.8 (#131)
| Benchmark | Command R | Grok-3 mini |
|---|---|---|
| LMArena Coding | 1169 | 1379 |
| Aider Polyglot | — | 49.3% |
| WeirdML | — | 42.6% |
| BigCodeBench Instruct | 37.1% | — |
| LiveBench Coding | 17.9% | — |
| BigCodeBench Complete | 45.2% | — |
Reasoning Too close to call
Command R: 13.8 (#331), Grok-3 mini: 13.6 (#334)
| Benchmark | Command R | Grok-3 mini |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1375 |
| ARC-AGI-2 | — | 0.4% |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 16.5% |
| LiveBench Reasoning | 21.9% | — |
| DTBench | 46.4% | — |
| LiveBench Data Analysis | 33.3% | — |
| LMCA | 9.2% | — |
| Epoch Capabilities Index | — | 140.35 |
| LiveBench | 27.5% | — |
Math Grok-3 mini leads
Command R: 28.0 (#246), Grok-3 mini: 42.1 (#85)
| Benchmark | Command R | Grok-3 mini |
|---|---|---|
| LMArena Math | 1155 | 1386 |
| OTIS Mock AIME 2024-2025 | — | 77.8% |
| Omni-MATH | — | 31.8% |
| LiveBench Math | 19.4% | — |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
Knowledge Grok-3 mini leads
Command R: 31.0 (#221), Grok-3 mini: 46.4 (#81)
| Benchmark | Command R | Grok-3 mini |
|---|---|---|
| LMArena Expert | 1138 | 1395 |
| GPQA Diamond | — | 76.3% |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| GPQA (HELM) | — | 67.5% |
| MMLU | 65.2% | — |
Multilingual Grok-3 mini leads
Command R: 35.7 (#245), Grok-3 mini: 48.1 (#145)
| Benchmark | Command R | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1174 | 1352 |
| LMArena Chinese | 1182 | 1387 |
| LMArena French | 1162 | 1357 |
| LMArena German | 1176 | 1349 |
| LMArena Japanese | 1143 | 1342 |
| LMArena Korean | 1163 | 1335 |
| LMArena Russian | 1174 | 1353 |
| LMArena Spanish | 1151 | 1381 |
Instruction Following Grok-3 mini leads
Command R: 58.1 (#261), Grok-3 mini: 78.5 (#9)
| Benchmark | Command R | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1167 | 1357 |
| LiveBench Instruction Following | 55.6% | — |
| IFEval | — | 95.1% |
Long Context Grok-3 mini leads
Command R: 36.3 (#231), Grok-3 mini: 41.0 (#147)
| Benchmark | Command R | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1198 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Grok-3 mini leads
Command R: 38.2 (#254), Grok-3 mini: 52.5 (#169)
| Benchmark | Command R | Grok-3 mini |
|---|---|---|
| LMArena Text | 1187 | 1370 |
| LMArena Creative Writing | 1170 | 1342 |
| LMArena Multi-Turn | 1163 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| WildBench | — | 65.1% |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than Grok-3 mini?
Grok-3 mini is the stronger model overall, scoring 41.2 to 31.4 on the Noometry Index.
Is Command R or Grok-3 mini better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.8 versus 29.3 in the Noometry coding category.
How many benchmarks do Command R and Grok-3 mini share?
17 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Grok-3 mini has 35.