Model comparison
Command R vs Mistral Small
Mistral Small is the stronger model overall, scoring 33.4 to 31.4 on the Noometry Index.
Last verified . 29 shared benchmarks.
Cohere
Mistral AISummary
- They share 29 benchmarks with published results for both. Command R scores higher in 2 categories and Mistral Small in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Small leads 52.5 to 38.2.
- The biggest single-benchmark swing is DTBench: 46.4% for Command R and 70.9% for Mistral Small.
- Both cost about the same: $0.15 input and $0.60 output per million tokens.
- Mistral Small accepts more context: 262K tokens versus 128K.
Side by side
| Command R | Mistral Small | |
|---|---|---|
| Provider | Cohere | Mistral AI |
| Noometry Index | 31.4 | 33.4 |
| Released | 2024-08-30 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 256K |
| Input $ / M tokens | $0.15 | $0.15 |
| Output $ / M tokens | $0.60 | $0.60 |
| Results tracked | 29 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small leads
Command R: 29.3 (#306), Mistral Small: 34.0 (#247)
| Benchmark | Command R | Mistral Small |
|---|---|---|
| BigCodeBench Instruct | 37.1% | 36.1% |
| LiveBench Coding | 17.9% | 36.2% |
| LMArena Coding | 1169 | 1362 |
| BigCodeBench Complete | 45.2% | 46.6% |
| SciCode | — | 26.5% |
| ALE-Bench | — | 497.62 |
Agentic & Tool Use Not comparable
Command R: —, Mistral Small: 28.1 (#93)
| Benchmark | Command R | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
Reasoning Mistral Small leads
Command R: 13.8 (#331), Mistral Small: 19.8 (#250)
| Benchmark | Command R | Mistral Small |
|---|---|---|
| LiveBench Reasoning | 21.9% | 44.8% |
| LMArena Hard Prompts | 1164 | 1335 |
| DTBench | 46.4% | 70.9% |
| LiveBench Data Analysis | 33.3% | 53.7% |
| LMCA | 9.2% | 20.6% |
| LiveBench | 27.5% | 44% |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
Math Command R leads
Command R: 28.0 (#246), Mistral Small: 16.4 (#293)
| Benchmark | Command R | Mistral Small |
|---|---|---|
| LiveBench Math | 19.4% | 39.9% |
| LMArena Math | 1155 | 1341 |
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| MATH Level 5 | — | 46.8% |
Knowledge Too close to call
Command R: 31.0 (#221), Mistral Small: 31.0 (#222)
| Benchmark | Command R | Mistral Small |
|---|---|---|
| LMArena Expert | 1138 | 1291 |
| MMLU | 65.2% | 68.7% |
| GPQA Diamond | — | 47.5% |
| Vectara Hallucination Rate | — | 5.1% |
Multimodal Not comparable
Command R: —, Mistral Small: 33.5 (#96)
| Benchmark | Command R | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual Mistral Small leads
Command R: 35.7 (#245), Mistral Small: 45.5 (#169)
| Benchmark | Command R | Mistral Small |
|---|---|---|
| LMArena Non-English | 1174 | 1315 |
| LMArena Chinese | 1182 | 1340 |
| LMArena French | 1162 | 1337 |
| LMArena German | 1176 | 1340 |
| LMArena Japanese | 1143 | 1275 |
| LMArena Korean | 1163 | 1259 |
| LMArena Russian | 1174 | 1324 |
| LMArena Spanish | 1151 | 1346 |
Instruction Following Mistral Small leads
Command R: 58.1 (#261), Mistral Small: 66.4 (#209)
| Benchmark | Command R | Mistral Small |
|---|---|---|
| LiveBench Instruction Following | 55.6% | 63.7% |
| LMArena Instruction Following | 1167 | 1310 |
Long Context Mistral Small leads
Command R: 36.3 (#231), Mistral Small: 40.4 (#156)
| Benchmark | Command R | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1198 | 1327 |
Writing & Preference Mistral Small leads
Command R: 38.2 (#254), Mistral Small: 52.5 (#171)
| Benchmark | Command R | Mistral Small |
|---|---|---|
| LMArena Text | 1187 | 1338 |
| LMArena Creative Writing | 1170 | 1305 |
| LMArena Multi-Turn | 1163 | 1344 |
| LiveBench Language | 16.7% | 30.5% |
Frequently asked questions
Is Command R better than Mistral Small?
Mistral Small is the stronger model overall, scoring 33.4 to 31.4 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 $0.15 and $0.60.
Is Command R or Mistral Small better for coding?
Mistral Small scores higher on coding benchmarks: 34.0 versus 29.3 in the Noometry coding category.
Which has the bigger context window?
Mistral Small does, with 262K tokens against 128K.
How many benchmarks do Command R and Mistral Small share?
29 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Mistral Small has 39.