Model comparison
Command R+ vs Grok 4.6
Grok 4.6 is the stronger model overall, scoring 56.9 to 32.4 on the Noometry Index.
Last verified . 21 shared benchmarks.
CohereSummary
- They share 21 benchmarks with published results for both. Command R+ scores higher in 0 categories and Grok 4.6 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.6 leads 61.4 to 9.2.
- The biggest single-benchmark swing is SimpleBench: 17.4% for Command R+ and 75.9% for Grok 4.6.
- Grok 4.6 is cheaper at $2 / $6 per million input/output tokens, against $2.50 / $10 for Command R+.
- Grok 4.6 accepts more context: 500K tokens versus 128K.
- Command R+ has downloadable open weights; the other is API-only.
Side by side
| Command R+ | Grok 4.6 | |
|---|---|---|
| Provider | Cohere | xAI |
| Noometry Index | 32.4 | 56.9 |
| Released | 2024-08-30 | 2026-08-12 |
| Weights | Open | Proprietary |
| Context window | 128K | 500K |
| Max output | 4K | 500K |
| Input $ / M tokens | $2.50 | $2 |
| Output $ / M tokens | $10 | $6 |
| Results tracked | 34 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
Command R+: 29.1 (#309), Grok 4.6: 58.5 (#16)
| Benchmark | Command R+ | Grok 4.6 |
|---|---|---|
| LMArena Coding | 1187 | 1465 |
| DeepSWE | — | 67.5% |
| FrontierCode | — | 48% |
| CursorBench | — | 41.4% |
| LMArena WebDev | — | 1617 |
| FrontierSWE | — | 25.3% |
| SciCode | — | 56.5% |
| WeirdML | — | 67.3% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| ALE-Bench | — | 1,508 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, Grok 4.6: 39.4 (#27)
| Benchmark | Command R+ | Grok 4.6 |
|---|---|---|
| APEX-Agents | — | 65.3% |
| GDP.pdf | — | 17.2% |
| Vending-Bench 2 | — | 9,047 |
Reasoning Grok 4.6 leads
Command R+: 9.2 (#344), Grok 4.6: 61.4 (#20)
| Benchmark | Command R+ | Grok 4.6 |
|---|---|---|
| SimpleBench | 17.4% | 75.9% |
| LMArena Hard Prompts | 1186 | 1447 |
| DTBench | 54.9% | 97.3% |
| LMCA | 5% | 48.5% |
| Epoch Capabilities Index | 119.34 | 156.44 |
| ARC-AGI-2 | — | 67.1% |
| NYT Connections (extended) | — | 80% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 19.7% |
| Chess Puzzles | — | 40% |
| EBR-Bench | — | 30.5% |
| LiveBench Reasoning | 24.8% | — |
| Mystery Game Puzzles | — | 34% |
| LiveBench Data Analysis | 38.1% | — |
| LiveBench | 31.8% | — |
Math Grok 4.6 leads
Command R+: 28.9 (#242), Grok 4.6: 67.0 (#24)
| Benchmark | Command R+ | Grok 4.6 |
|---|---|---|
| LMArena Math | 1188 | 1423 |
| FrontierMath (Tiers 1-3) | — | 66% |
| FrontierMath Tier 4 | — | 31.7% |
| OTIS Mock AIME 2024-2025 | — | 99.2% |
| ProofBench | — | 51% |
| LiveBench Math | 21.3% | — |
Knowledge Grok 4.6 leads
Command R+: 36.4 (#169), Grok 4.6: 63.3 (#20)
| Benchmark | Command R+ | Grok 4.6 |
|---|---|---|
| LMArena Expert | 1174 | 1467 |
| GPQA Diamond | — | 94% |
| SimpleQA Verified | — | 49.3% |
| Vectara Hallucination Rate | 6.9% | — |
| MMLU | 69.4% | — |
Multimodal Not comparable
Command R+: —, Grok 4.6: 43.6 (#23)
| Benchmark | Command R+ | Grok 4.6 |
|---|---|---|
| LMArena Vision | — | 1263 |
| Blueprint-Bench 2 | — | 33.2% |
| Furniture Assembly | — | 40% |
| LMArena Document | — | 1452 |
Multilingual Grok 4.6 leads
Command R+: 38.6 (#227), Grok 4.6: 53.0 (#74)
| Benchmark | Command R+ | Grok 4.6 |
|---|---|---|
| LMArena Non-English | 1216 | 1420 |
| LMArena Chinese | 1226 | 1480 |
| LMArena French | 1209 | 1461 |
| LMArena German | 1216 | 1431 |
| LMArena Japanese | 1166 | 1376 |
| LMArena Korean | 1138 | 1397 |
| LMArena Russian | 1227 | 1422 |
| LMArena Spanish | 1189 | 1404 |
Instruction Following Grok 4.6 leads
Command R+: 60.0 (#254), Grok 4.6: 75.4 (#63)
| Benchmark | Command R+ | Grok 4.6 |
|---|---|---|
| LMArena Instruction Following | 1197 | 1431 |
| LiveBench Instruction Following | 57.6% | — |
Long Context Grok 4.6 leads
Command R+: 37.3 (#219), Grok 4.6: 44.5 (#66)
| Benchmark | Command R+ | Grok 4.6 |
|---|---|---|
| LMArena Longer Query | 1230 | 1454 |
Writing & Preference Grok 4.6 leads
Command R+: 43.5 (#228), Grok 4.6: 62.3 (#80)
| Benchmark | Command R+ | Grok 4.6 |
|---|---|---|
| LMArena Text | 1229 | 1428 |
| LMArena Creative Writing | 1235 | 1428 |
| LMArena Multi-Turn | 1213 | 1425 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than Grok 4.6?
Grok 4.6 is the stronger model overall, scoring 56.9 to 32.4 on the Noometry Index.
Which is cheaper, Command R+ or Grok 4.6?
Grok 4.6 is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or Grok 4.6 better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
Grok 4.6 does, with 500K tokens against 128K.
How many benchmarks do Command R+ and Grok 4.6 share?
21 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Grok 4.6 has 49.