Model comparison
Mistral Large 4 vs Mistral Small
Mistral Large 4 is the stronger model overall, scoring 43.1 to 33.4 on the Noometry Index. Mistral Small costs 3.9× less per token, which makes it the better buy when Mistral Large 4's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
Mistral AISummary
- They share 12 benchmarks with published results for both. Mistral Large 4 scores higher in 8 categories and Mistral Small in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Large 4 leads 40.4 to 16.4.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.68 / $2.09 for Mistral Large 4.
- Mistral Large 4 accepts more context: 1.05M tokens versus 262K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| Mistral Large 4 | Mistral Small | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 43.1 | 33.4 |
| Released | 2026-10-06 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 262K | 256K |
| Input $ / M tokens | $0.68 | $0.15 |
| Output $ / M tokens | $2.09 | $0.60 |
| Results tracked | 15 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 4 leads
Mistral Large 4: 48.6 (#57), Mistral Small: 34.0 (#247)
| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| LMArena Coding | 1475 | 1362 |
| LMArena WebDev | 1541 | — |
| SciCode | — | 26.5% |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |
Agentic & Tool Use Not comparable
Mistral Large 4: —, Mistral Small: 28.1 (#93)
| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
Reasoning Mistral Large 4 leads
Mistral Large 4: 22.5 (#192), Mistral Small: 19.8 (#250)
| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| LMArena Hard Prompts | 1444 | 1335 |
| Kagi LLM Benchmark | — | 37.8% |
| NYT Connections (extended) | 27.4% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| LiveBench | — | 44% |
Math Mistral Large 4 leads
Mistral Large 4: 40.4 (#91), Mistral Small: 16.4 (#293)
| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| LMArena Math | 1488 | 1341 |
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |
Knowledge Mistral Large 4 leads
Mistral Large 4: 36.6 (#166), Mistral Small: 31.0 (#222)
| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| LMArena Expert | 1447 | 1291 |
| GPQA Diamond | — | 47.5% |
| SimpleQA Verified | 20% | — |
| Vectara Hallucination Rate | — | 5.1% |
| MMLU | — | 68.7% |
Multimodal Not comparable
Mistral Large 4: —, Mistral Small: 33.5 (#96)
| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual Mistral Large 4 leads
Mistral Large 4: 52.6 (#82), Mistral Small: 45.5 (#169)
| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| LMArena Non-English | 1415 | 1315 |
| LMArena Chinese | 1491 | 1340 |
| LMArena Russian | 1414 | 1324 |
| LMArena French | — | 1337 |
| LMArena German | — | 1340 |
| LMArena Japanese | — | 1275 |
| LMArena Korean | — | 1259 |
| LMArena Spanish | — | 1346 |
Instruction Following Mistral Large 4 leads
Mistral Large 4: 75.0 (#76), Mistral Small: 66.4 (#209)
| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1424 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context Mistral Large 4 leads
Mistral Large 4: 43.6 (#89), Mistral Small: 40.4 (#156)
| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1429 | 1327 |
Writing & Preference Mistral Large 4 leads
Mistral Large 4: 60.4 (#97), Mistral Small: 52.5 (#171)
| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| LMArena Text | 1427 | 1338 |
| LMArena Creative Writing | 1361 | 1305 |
| LMArena Multi-Turn | 1424 | 1344 |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is Mistral Large 4 better than Mistral Small?
Mistral Large 4 is the stronger model overall, scoring 43.1 to 33.4 on the Noometry Index. Mistral Small costs 3.9× less per token, which makes it the better buy when Mistral Large 4's lead doesn't matter for your workload.
Which is cheaper, Mistral Large 4 or Mistral Small?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Mistral Large 4 lists at $0.68 and $2.09.
Is Mistral Large 4 or Mistral Small better for coding?
Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 4 does, with 1.05M tokens against 262K.
How many benchmarks do Mistral Large 4 and Mistral Small share?
12 benchmarks have published results for both models. Mistral Large 4 has 15 scored results on Noometry and Mistral Small has 39.