Model comparison
Command R vs Granite 4.0 H Small
Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 31.4 on the Noometry Index.
Last verified . 13 shared benchmarks.
CohereSummary
- They share 13 benchmarks with published results for both. Command R scores higher in 0 categories and Granite 4.0 H Small in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Granite 4.0 H Small leads 68.7 to 58.1.
Side by side
| Command R | Granite 4.0 H Small | |
|---|---|---|
| Provider | Cohere | IBM |
| Noometry Index | 31.4 | 36.5 |
| Released | 2024-08-30 | — |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 29 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.0 H Small leads
Command R: 29.3 (#306), Granite 4.0 H Small: 36.4 (#209)
| Benchmark | Command R | Granite 4.0 H Small |
|---|---|---|
| LMArena Coding | 1169 | 1249 |
| BigCodeBench Instruct | 37.1% | — |
| LiveBench Coding | 17.9% | — |
| BigCodeBench Complete | 45.2% | — |
Reasoning Granite 4.0 H Small leads
Command R: 13.8 (#331), Granite 4.0 H Small: 24.4 (#163)
| Benchmark | Command R | Granite 4.0 H Small |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1240 |
| LiveBench Reasoning | 21.9% | — |
| DTBench | 46.4% | — |
| LiveBench Data Analysis | 33.3% | — |
| LMCA | 9.2% | — |
| LiveBench | 27.5% | — |
Math Granite 4.0 H Small leads
Command R: 28.0 (#246), Granite 4.0 H Small: 31.4 (#223)
| Benchmark | Command R | Granite 4.0 H Small |
|---|---|---|
| LMArena Math | 1155 | 1247 |
| Omni-MATH | — | 29.6% |
| LiveBench Math | 19.4% | — |
Knowledge Too close to call
Command R: 31.0 (#221), Granite 4.0 H Small: 32.0 (#215)
| Benchmark | Command R | Granite 4.0 H Small |
|---|---|---|
| LMArena Expert | 1138 | 1251 |
| MMLU-Pro | — | 56.9% |
| Vectara Hallucination Rate | — | 5.2% |
| GPQA (HELM) | — | 38.3% |
| MMLU | 65.2% | — |
Multilingual Granite 4.0 H Small leads
Command R: 35.7 (#245), Granite 4.0 H Small: 38.6 (#228)
| Benchmark | Command R | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | 1174 | 1216 |
| LMArena Chinese | 1182 | 1249 |
| LMArena Russian | 1174 | 1201 |
| LMArena Spanish | 1151 | 1258 |
| LMArena French | 1162 | — |
| LMArena German | 1176 | — |
| LMArena Japanese | 1143 | — |
| LMArena Korean | 1163 | — |
Instruction Following Granite 4.0 H Small leads
Command R: 58.1 (#261), Granite 4.0 H Small: 68.7 (#183)
| Benchmark | Command R | Granite 4.0 H Small |
|---|---|---|
| LMArena Instruction Following | 1167 | 1222 |
| LiveBench Instruction Following | 55.6% | — |
| IFEval | — | 89% |
Long Context Granite 4.0 H Small leads
Command R: 36.3 (#231), Granite 4.0 H Small: 37.7 (#213)
| Benchmark | Command R | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | 1198 | 1242 |
Writing & Preference Granite 4.0 H Small leads
Command R: 38.2 (#254), Granite 4.0 H Small: 43.8 (#227)
| Benchmark | Command R | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | 1187 | 1241 |
| LMArena Creative Writing | 1170 | 1211 |
| LMArena Multi-Turn | 1163 | 1242 |
| WildBench | — | 73.9% |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than Granite 4.0 H Small?
Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 31.4 on the Noometry Index.
Is Command R or Granite 4.0 H Small better for coding?
Granite 4.0 H Small scores higher on coding benchmarks: 36.4 versus 29.3 in the Noometry coding category.
How many benchmarks do Command R and Granite 4.0 H Small share?
13 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Granite 4.0 H Small has 19.