Model comparison
Command R+ vs Mistral Small
Mistral Small is the stronger model overall, scoring 33.1 to 32.0 on the Noometry Index.
Last verified . 30 shared benchmarks.
Cohere
Mistral AISummary
- They share 30 benchmarks with published results for both. Command R+ scores higher in 2 categories and Mistral Small in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Command R+ leads 26.6 to 15.4.
- The biggest single-benchmark swing is LiveBench Reasoning: 24.8% for Command R+ and 44.8% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $2.50 / $10 for Command R+.
- Mistral Small accepts more context: 256K tokens versus 128K.
Side by side
| Command R+ | Mistral Small | |
|---|---|---|
| Provider | Cohere | Mistral AI |
| Noometry Index | 32.0 | 33.1 |
| Released | 2024-08-30 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 128K | 256K |
| Max output | 4K | 256K |
| Input $ / M tokens | $2.50 | $0.15 |
| Output $ / M tokens | $10 | $0.60 |
| Results tracked | 34 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small leads
Command R+: 28.6 (#304), Mistral Small: 33.5 (#242)
| Benchmark | Command R+ | Mistral Small |
|---|---|---|
| BigCodeBench Instruct | 33.8% | 36.1% |
| LiveBench Coding | 19.1% | 36.2% |
| LMArena Coding | 1187 | 1363 |
| BigCodeBench Complete | 41.9% | 46.6% |
| SciCode | — | 26.5% |
| ALE-Bench | — | 497.62 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, Mistral Small: 27.9 (#87)
| Benchmark | Command R+ | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
Reasoning Mistral Small leads
Command R+: 8.9 (#341), Mistral Small: 19.3 (#238)
| Benchmark | Command R+ | Mistral Small |
|---|---|---|
| LiveBench Reasoning | 24.8% | 44.8% |
| LMArena Hard Prompts | 1186 | 1336 |
| DTBench | 54.9% | 70.9% |
| LiveBench Data Analysis | 38.1% | 53.7% |
| LMCA | 5% | 20.6% |
| LiveBench | 31.8% | 44% |
| SimpleBench | 17.4% | — |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| Epoch Capabilities Index | 119.28 | — |
Math Command R+ leads
Command R+: 26.6 (#239), Mistral Small: 15.4 (#287)
| Benchmark | Command R+ | Mistral Small |
|---|---|---|
| LiveBench Math | 21.3% | 39.9% |
| LMArena Math | 1188 | 1341 |
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| MATH Level 5 | — | 46.8% |
Knowledge Command R+ leads
Command R+: 35.9 (#165), Mistral Small: 30.9 (#214)
| Benchmark | Command R+ | Mistral Small |
|---|---|---|
| Vectara Hallucination Rate | 6.9% | 5.1% |
| LMArena Expert | 1174 | 1293 |
| MMLU | 69.4% | 68.7% |
| GPQA Diamond | — | 47.5% |
Multimodal Not comparable
Command R+: —, Mistral Small: 32.9 (#91)
| Benchmark | Command R+ | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual Mistral Small leads
Command R+: 38.8 (#222), Mistral Small: 45.7 (#164)
| Benchmark | Command R+ | Mistral Small |
|---|---|---|
| LMArena Non-English | 1216 | 1315 |
| LMArena Chinese | 1226 | 1342 |
| LMArena French | 1208 | 1337 |
| LMArena German | 1216 | 1341 |
| LMArena Japanese | 1166 | 1275 |
| LMArena Korean | 1138 | 1260 |
| LMArena Russian | 1227 | 1324 |
| LMArena Spanish | 1189 | 1346 |
Instruction Following Mistral Small leads
Command R+: 60.2 (#249), Mistral Small: 66.6 (#204)
| Benchmark | Command R+ | Mistral Small |
|---|---|---|
| LiveBench Instruction Following | 57.6% | 63.7% |
| LMArena Instruction Following | 1197 | 1310 |
Long Context Mistral Small leads
Command R+: 37.3 (#214), Mistral Small: 40.4 (#151)
| Benchmark | Command R+ | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1231 | 1327 |
Writing & Preference Mistral Small leads
Command R+: 43.7 (#223), Mistral Small: 52.6 (#165)
| Benchmark | Command R+ | Mistral Small |
|---|---|---|
| LMArena Text | 1229 | 1338 |
| LMArena Creative Writing | 1235 | 1304 |
| LMArena Multi-Turn | 1213 | 1344 |
| LiveBench Language | 29.7% | 30.5% |
Frequently asked questions
Is Command R+ better than Mistral Small?
Mistral Small is the stronger model overall, scoring 33.1 to 32.0 on the Noometry Index.
Which is cheaper, Command R+ or Mistral Small?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or Mistral Small better for coding?
Mistral Small scores higher on coding benchmarks: 33.5 versus 28.6 in the Noometry coding category.
Which has the bigger context window?
Mistral Small does, with 256K tokens against 128K.
How many benchmarks do Command R+ and Mistral Small share?
30 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Mistral Small has 39.