Model comparison
Command R vs Mistral Medium
Mistral Medium is the stronger model overall, scoring 36.0 to 31.0 on the Noometry Index. Command R costs 11× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Cohere
Mistral AISummary
- They share 19 benchmarks with published results for both. Command R scores higher in 1 category and Mistral Medium in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.2 to 38.4.
- The biggest single-benchmark swing is DTBench: 46.4% for Command R and 75.5% for Mistral Medium.
- Command R is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 128K.
Side by side
| Command R | Mistral Medium | |
|---|---|---|
| Provider | Cohere | Mistral AI |
| Noometry Index | 31.0 | 36.0 |
| Released | 2024-08-30 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 262K |
| Input $ / M tokens | $0.15 | $1.50 |
| Output $ / M tokens | $0.60 | $7.50 |
| Results tracked | 29 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium leads
Command R: 28.8 (#301), Mistral Medium: 33.8 (#241)
| Benchmark | Command R | Mistral Medium |
|---|---|---|
| LMArena Coding | 1170 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| BigCodeBench Instruct | 37.1% | — |
| LiveBench Coding | 17.9% | — |
| BigCodeBench Complete | 45.2% | — |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Not comparable
Command R: —, Mistral Medium: 28.1 (#84)
| Benchmark | Command R | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning Mistral Medium leads
Command R: 13.3 (#329), Mistral Medium: 23.3 (#165)
| Benchmark | Command R | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1426 |
| DTBench | 46.4% | 75.5% |
| LMCA | 9.2% | 26.1% |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| LiveBench Reasoning | 21.9% | — |
| LiveBench Data Analysis | 33.3% | — |
| Surface Evolver Bench | — | 26.9% |
| LiveBench | 27.5% | — |
Math Mistral Medium leads
Command R: 25.8 (#244), Mistral Medium: 27.2 (#238)
| Benchmark | Command R | Mistral Medium |
|---|---|---|
| LMArena Math | 1155 | 1409 |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| LiveBench Math | 19.4% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Command R leads
Command R: 30.5 (#219), Mistral Medium: 24.9 (#260)
| Benchmark | Command R | Mistral Medium |
|---|---|---|
| LMArena Expert | 1138 | 1408 |
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
| MMLU | 65.2% | — |
Multimodal Not comparable
Command R: —, Mistral Medium: 34.6 (#82)
| Benchmark | Command R | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Mistral Medium leads
Command R: 35.9 (#240), Mistral Medium: 52.3 (#86)
| Benchmark | Command R | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1174 | 1408 |
| LMArena Chinese | 1182 | 1448 |
| LMArena French | 1161 | 1460 |
| LMArena German | 1176 | 1433 |
| LMArena Japanese | 1143 | 1378 |
| LMArena Korean | 1162 | 1382 |
| LMArena Russian | 1174 | 1411 |
| LMArena Spanish | 1150 | 1433 |
Instruction Following Mistral Medium leads
Command R: 58.3 (#256), Mistral Medium: 73.9 (#111)
| Benchmark | Command R | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1167 | 1398 |
| LiveBench Instruction Following | 55.6% | — |
Long Context Mistral Medium leads
Command R: 36.3 (#226), Mistral Medium: 42.9 (#108)
| Benchmark | Command R | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1198 | 1406 |
Writing & Preference Mistral Medium leads
Command R: 38.4 (#248), Mistral Medium: 60.2 (#97)
| Benchmark | Command R | Mistral Medium |
|---|---|---|
| LMArena Text | 1187 | 1424 |
| LMArena Creative Writing | 1170 | 1391 |
| LMArena Multi-Turn | 1163 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than Mistral Medium?
Mistral Medium is the stronger model overall, scoring 36.0 to 31.0 on the Noometry Index. Command R costs 11× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Which is cheaper, Command R or Mistral Medium?
Command R is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Command R or Mistral Medium better for coding?
Mistral Medium scores higher on coding benchmarks: 33.8 versus 28.8 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 128K.
How many benchmarks do Command R and Mistral Medium share?
19 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Mistral Medium has 36.