Model comparison
Mistral Large vs Mistral Medium 3.5
Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 31.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. Mistral Large scores higher in 0 categories and Mistral Medium 3.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Medium 3.5 leads 36.4 to 17.1.
- Both cost about the same: $2 input and $6 output per million tokens.
- Mistral Medium 3.5 accepts more context: 262K tokens versus 131K.
Side by side
| Mistral Large | Mistral Medium 3.5 | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 31.6 | 39.6 |
| Released | 2024-02-26 | — |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 16K | 210K |
| Input $ / M tokens | $2 | $1.50 |
| Output $ / M tokens | $6 | $7.50 |
| Results tracked | 51 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium 3.5 leads
Mistral Large: 33.8 (#240), Mistral Medium 3.5: 35.7 (#208)
| Benchmark | Mistral Large | Mistral Medium 3.5 |
|---|---|---|
| LMArena Coding | 1277 | 1461 |
| LMArena WebDev | — | 1263 |
| SciCode | 36.2% | — |
| BigCodeBench Instruct | 30% | — |
| LiveBench Coding | 47.1% | — |
| BigCodeBench Complete | 38.3% | — |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |
Agentic & Tool Use Not comparable
Mistral Large: 28.4 (#83), Mistral Medium 3.5: —
| Benchmark | Mistral Large | Mistral Medium 3.5 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
Reasoning Mistral Medium 3.5 leads
Mistral Large: 15.4 (#305), Mistral Medium 3.5: 16.6 (#290)
| Benchmark | Mistral Large | Mistral Medium 3.5 |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1436 |
| Epoch Capabilities Index | 128.52 | 141.42 |
| SimpleBench | 22.5% | — |
| Kagi LLM Benchmark | — | 41.4% |
| NYT Connections (extended) | — | 12.9% |
| CritPt | 0% | — |
| LiveBench Reasoning | 43.5% | — |
| DTBench | 65.1% | — |
| LiveBench Data Analysis | 50.1% | — |
| LMCA | 16.7% | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Mistral Medium 3.5 leads
Mistral Large: 17.1 (#285), Mistral Medium 3.5: 36.4 (#113)
| Benchmark | Mistral Large | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1262 | 1432 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Mistral Medium 3.5 leads
Mistral Large: 30.0 (#224), Mistral Medium 3.5: 39.3 (#123)
| Benchmark | Mistral Large | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1232 | 1431 |
| GPQA Diamond | 51.3% | — |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |
Multimodal Not comparable
Mistral Large: —, Mistral Medium 3.5: 37.6 (#64)
| Benchmark | Mistral Large | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | — | 1222 |
Multilingual Mistral Medium 3.5 leads
Mistral Large: 40.1 (#214), Mistral Medium 3.5: 52.1 (#93)
| Benchmark | Mistral Large | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1237 | 1405 |
| LMArena Chinese | 1240 | 1443 |
| LMArena French | 1324 | 1448 |
| LMArena German | 1254 | 1453 |
| LMArena Korean | 1202 | 1387 |
| LMArena Russian | 1257 | 1396 |
| LMArena Spanish | 1268 | 1406 |
| LMArena Japanese | 1187 | — |
Instruction Following Mistral Medium 3.5 leads
Mistral Large: 68.1 (#186), Mistral Medium 3.5: 74.7 (#87)
| Benchmark | Mistral Large | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1249 | 1414 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
Long Context Mistral Medium 3.5 leads
Mistral Large: 38.3 (#194), Mistral Medium 3.5: 43.2 (#101)
| Benchmark | Mistral Large | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1262 | 1414 |
Writing & Preference Mistral Medium 3.5 leads
Mistral Large: 40.9 (#237), Mistral Medium 3.5: 58.6 (#113)
| Benchmark | Mistral Large | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1266 | 1421 |
| LMArena Creative Writing | 1243 | 1372 |
| LMArena Multi-Turn | 1260 | 1423 |
| Short-Story Creative Writing | 69% | — |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |
| EQ-Bench 4 | — | 993 |
| LiveBench Language | 39.4% | — |
Frequently asked questions
Is Mistral Large better than Mistral Medium 3.5?
Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 31.6 on the Noometry Index.
Which is cheaper, Mistral Large or Mistral Medium 3.5?
Mistral Medium 3.5 is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; Mistral Large lists at $2 and $6.
Is Mistral Large or Mistral Medium 3.5 better for coding?
Mistral Medium 3.5 scores higher on coding benchmarks: 35.7 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium 3.5 does, with 262K tokens against 131K.
How many benchmarks do Mistral Large and Mistral Medium 3.5 share?
17 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Mistral Medium 3.5 has 22.