Model comparison
Command R+ vs Gemma 4 31B IT
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 32.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
Cohere
GoogleSummary
- They share 18 benchmarks with published results for both. Command R+ scores higher in 0 categories and Gemma 4 31B IT in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemma 4 31B IT leads 27.2 to 9.2.
- The biggest single-benchmark swing is LMCA: 5% for Command R+ and 39.3% for Gemma 4 31B IT.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $2.50 / $10 for Command R+.
- Gemma 4 31B IT accepts more context: 262K tokens versus 128K.
Side by side
| Command R+ | Gemma 4 31B IT | |
|---|---|---|
| Provider | Cohere | |
| Noometry Index | 32.4 | 43.5 |
| Released | 2024-08-30 | 2026-04-02 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 33K |
| Input $ / M tokens | $2.50 | $0.09 |
| Output $ / M tokens | $10 | $0.34 |
| Results tracked | 34 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Command R+: 29.1 (#309), Gemma 4 31B IT: 42.3 (#108)
| Benchmark | Command R+ | Gemma 4 31B IT |
|---|---|---|
| LMArena Coding | 1187 | 1459 |
| LMArena WebDev | — | 1366 |
| SciCode | — | 43.4% |
| WeirdML | — | 52.3% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| ALE-Bench | — | 925.5 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Reasoning Gemma 4 31B IT leads
Command R+: 9.2 (#344), Gemma 4 31B IT: 27.2 (#122)
| Benchmark | Command R+ | Gemma 4 31B IT |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1448 |
| DTBench | 54.9% | 82.7% |
| LMCA | 5% | 39.3% |
| Epoch Capabilities Index | 119.34 | 142.74 |
| SimpleBench | 17.4% | — |
| Kagi LLM Benchmark | — | 63.5% |
| NYT Connections (extended) | — | 70.6% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 5% |
| Thematic Generalization | — | 53% |
| LiveBench Reasoning | 24.8% | — |
| LiveBench Data Analysis | 38.1% | — |
| Surface Evolver Bench | — | 30.6% |
| LiveBench | 31.8% | — |
Math Gemma 4 31B IT leads
Command R+: 28.9 (#242), Gemma 4 31B IT: 43.2 (#81)
| Benchmark | Command R+ | Gemma 4 31B IT |
|---|---|---|
| LMArena Math | 1188 | 1465 |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| LiveBench Math | 21.3% | — |
Knowledge Gemma 4 31B IT leads
Command R+: 36.4 (#169), Gemma 4 31B IT: 37.9 (#151)
| Benchmark | Command R+ | Gemma 4 31B IT |
|---|---|---|
| Vectara Hallucination Rate | 6.9% | 7.4% |
| LMArena Expert | 1174 | 1465 |
| GPQA Diamond | — | 75.8% |
| SimpleQA Verified | — | 10.4% |
| MMLU | 69.4% | — |
Multimodal Not comparable
Command R+: —, Gemma 4 31B IT: 41.6 (#34)
| Benchmark | Command R+ | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | — | 1277 |
| LMArena Document | — | 1425 |
Multilingual Gemma 4 31B IT leads
Command R+: 38.6 (#227), Gemma 4 31B IT: 53.8 (#57)
| Benchmark | Command R+ | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1216 | 1431 |
| LMArena Chinese | 1226 | 1476 |
| LMArena French | 1209 | 1435 |
| LMArena Russian | 1227 | 1460 |
| LMArena Spanish | 1189 | 1444 |
| LMArena German | 1216 | — |
| LMArena Japanese | 1166 | — |
| LMArena Korean | 1138 | — |
Instruction Following Gemma 4 31B IT leads
Command R+: 60.0 (#254), Gemma 4 31B IT: 75.5 (#61)
| Benchmark | Command R+ | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1197 | 1433 |
| LiveBench Instruction Following | 57.6% | — |
Long Context Gemma 4 31B IT leads
Command R+: 37.3 (#219), Gemma 4 31B IT: 44.2 (#71)
| Benchmark | Command R+ | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1230 | 1446 |
Writing & Preference Gemma 4 31B IT leads
Command R+: 43.5 (#228), Gemma 4 31B IT: 60.5 (#96)
| Benchmark | Command R+ | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1229 | 1443 |
| LMArena Creative Writing | 1235 | 1415 |
| LMArena Multi-Turn | 1213 | 1452 |
| EQ-Bench Creative Writing | — | 1368 |
| EQ-Bench 4 | — | 1120 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than Gemma 4 31B IT?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 32.4 on the Noometry Index.
Which is cheaper, Command R+ or Gemma 4 31B IT?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or Gemma 4 31B IT better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
Gemma 4 31B IT does, with 262K tokens against 128K.
How many benchmarks do Command R+ and Gemma 4 31B IT share?
18 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Gemma 4 31B IT has 35.