Model comparison
Command R+ vs Grok 4.3
Grok 4.3 is the stronger model overall, scoring 43.8 to 32.4 on the Noometry Index.
Last verified . 20 shared benchmarks.
CohereSummary
- They share 20 benchmarks with published results for both. Command R+ scores higher in 0 categories and Grok 4.3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.3 leads 35.9 to 9.2.
- The biggest single-benchmark swing is DTBench: 54.9% for Command R+ and 90.7% for Grok 4.3.
- Grok 4.3 is cheaper at $1.25 / $2.50 per million input/output tokens, against $2.50 / $10 for Command R+.
- Grok 4.3 accepts more context: 1M tokens versus 128K.
- Command R+ has downloadable open weights; the other is API-only.
Side by side
| Command R+ | Grok 4.3 | |
|---|---|---|
| Provider | Cohere | xAI |
| Noometry Index | 32.4 | 43.8 |
| Released | 2024-08-30 | 2026-04-17 |
| Weights | Open | Proprietary |
| Context window | 128K | 1M |
| Max output | 4K | 30K |
| Input $ / M tokens | $2.50 | $1.25 |
| Output $ / M tokens | $10 | $2.50 |
| Results tracked | 34 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.3 leads
Command R+: 29.1 (#309), Grok 4.3: 41.6 (#121)
| Benchmark | Command R+ | Grok 4.3 |
|---|---|---|
| LMArena Coding | 1187 | 1415 |
| LMArena WebDev | — | 1357 |
| SciCode | — | 47.3% |
| WeirdML | — | 49.9% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| ALE-Bench | — | 944.17 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, Grok 4.3: 27.7 (#99)
| Benchmark | Command R+ | Grok 4.3 |
|---|---|---|
| GDP.pdf | — | 8% |
| LMArena Search | — | 1165 |
| Vending-Bench 2 | — | 35.26 |
Reasoning Grok 4.3 leads
Command R+: 9.2 (#344), Grok 4.3: 35.9 (#68)
| Benchmark | Command R+ | Grok 4.3 |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1396 |
| DTBench | 54.9% | 90.7% |
| LMCA | 5% | 38.3% |
| Epoch Capabilities Index | 119.34 | 149.16 |
| SimpleBench | 17.4% | — |
| NYT Connections (extended) | — | 55.2% |
| CritPt | — | 8% |
| Chess Puzzles | — | 25% |
| LiveBench Reasoning | 24.8% | — |
| LiveBench Data Analysis | 38.1% | — |
| ForecastBench | — | 60.3 |
| LiveBench | 31.8% | — |
Math Grok 4.3 leads
Command R+: 28.9 (#242), Grok 4.3: 46.0 (#74)
| Benchmark | Command R+ | Grok 4.3 |
|---|---|---|
| LMArena Math | 1188 | 1388 |
| FrontierMath (Tiers 1-3) | — | 42.8% |
| FrontierMath Tier 4 | — | 14.6% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| ProofBench | — | 11% |
| LiveBench Math | 21.3% | — |
Knowledge Grok 4.3 leads
Command R+: 36.4 (#169), Grok 4.3: 52.5 (#62)
| Benchmark | Command R+ | Grok 4.3 |
|---|---|---|
| LMArena Expert | 1174 | 1385 |
| GPQA Diamond | — | 88.8% |
| SimpleQA Verified | — | 33.2% |
| Vectara Hallucination Rate | 6.9% | — |
| MMLU | 69.4% | — |
Multimodal Not comparable
Command R+: —, Grok 4.3: 31.6 (#104)
| Benchmark | Command R+ | Grok 4.3 |
|---|---|---|
| LMArena Vision | — | 1229 |
| Blueprint-Bench 2 | — | 0% |
Multilingual Grok 4.3 leads
Command R+: 38.6 (#227), Grok 4.3: 50.5 (#120)
| Benchmark | Command R+ | Grok 4.3 |
|---|---|---|
| LMArena Non-English | 1216 | 1385 |
| LMArena Chinese | 1226 | 1422 |
| LMArena French | 1209 | 1412 |
| LMArena German | 1216 | 1395 |
| LMArena Japanese | 1166 | 1379 |
| LMArena Korean | 1138 | 1356 |
| LMArena Russian | 1227 | 1399 |
| LMArena Spanish | 1189 | 1398 |
Instruction Following Grok 4.3 leads
Command R+: 60.0 (#254), Grok 4.3: 72.1 (#140)
| Benchmark | Command R+ | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | 1197 | 1366 |
| LiveBench Instruction Following | 57.6% | — |
Long Context Grok 4.3 leads
Command R+: 37.3 (#219), Grok 4.3: 42.5 (#123)
| Benchmark | Command R+ | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | 1230 | 1393 |
Writing & Preference Grok 4.3 leads
Command R+: 43.5 (#228), Grok 4.3: 58.5 (#118)
| Benchmark | Command R+ | Grok 4.3 |
|---|---|---|
| LMArena Text | 1229 | 1397 |
| LMArena Creative Writing | 1235 | 1380 |
| LMArena Multi-Turn | 1213 | 1406 |
| EQ-Bench 4 | — | 1075 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than Grok 4.3?
Grok 4.3 is the stronger model overall, scoring 43.8 to 32.4 on the Noometry Index.
Which is cheaper, Command R+ or Grok 4.3?
Grok 4.3 is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or Grok 4.3 better for coding?
Grok 4.3 scores higher on coding benchmarks: 41.6 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
Grok 4.3 does, with 1M tokens against 128K.
How many benchmarks do Command R+ and Grok 4.3 share?
20 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Grok 4.3 has 40.