Model comparison
Llama 3.1-70B vs Mistral Small 3.1
Mistral Small 3.1 is the stronger model overall, scoring 31.7 to 29.6 on the Noometry Index.
Last verified . 26 shared benchmarks.
Meta
Mistral AISummary
- They share 26 benchmarks with published results for both. Llama 3.1-70B scores higher in 3 categories and Mistral Small 3.1 in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Mistral Small 3.1 leads 38.3 to 30.3.
- The biggest single-benchmark swing is IFEval: 82.1% for Llama 3.1-70B and 75% for Mistral Small 3.1.
- Both cost about the same: $0.40 input and $0.40 output per million tokens.
Side by side
| Llama 3.1-70B | Mistral Small 3.1 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 29.6 | 31.7 |
| Released | 2024-07-23 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 128K | 128K |
| Max output | 4K | 102K |
| Input $ / M tokens | $0.40 | $0.35 |
| Output $ / M tokens | $0.40 | $0.56 |
| Results tracked | 35 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3.1 leads
Llama 3.1-70B: 30.3 (#296), Mistral Small 3.1: 38.3 (#179)
| Benchmark | Llama 3.1-70B | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1260 | 1309 |
| WeirdML | 9% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 54.8% | — |
Agentic & Tool Use Not comparable
Llama 3.1-70B: 25.1 (#112), Mistral Small 3.1: —
| Benchmark | Llama 3.1-70B | Mistral Small 3.1 |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
Reasoning Llama 3.1-70B leads
Llama 3.1-70B: 21.6 (#220), Mistral Small 3.1: 19.7 (#254)
| Benchmark | Llama 3.1-70B | Mistral Small 3.1 |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1278 |
| Epoch Capabilities Index | 125.92 | 127.48 |
| Chess Puzzles | — | 1% |
| DTBench | 60% | — |
| LMCA | 14.8% | — |
Math Mistral Small 3.1 leads
Llama 3.1-70B: 13.5 (#304), Mistral Small 3.1: 14.7 (#301)
| Benchmark | Llama 3.1-70B | Mistral Small 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 3.6% | 3.9% |
| Omni-MATH | 21% | 24.8% |
| LMArena Math | 1252 | 1262 |
| MATH Level 5 | 36.7% | — |
Knowledge Llama 3.1-70B leads
Llama 3.1-70B: 24.2 (#269), Mistral Small 3.1: 22.6 (#271)
| Benchmark | Llama 3.1-70B | Mistral Small 3.1 |
|---|---|---|
| GPQA Diamond | 44.2% | 41.9% |
| MMLU-Pro | 65.3% | 61% |
| GPQA (HELM) | 42.6% | 39.2% |
| LMArena Expert | 1209 | 1257 |
| MMLU | 80.1% | — |
Multimodal Not comparable
Llama 3.1-70B: —, Mistral Small 3.1: 33.2 (#99)
| Benchmark | Llama 3.1-70B | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | — | 1136 |
Multilingual Mistral Small 3.1 leads
Llama 3.1-70B: 38.8 (#225), Mistral Small 3.1: 41.2 (#209)
| Benchmark | Llama 3.1-70B | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1219 | 1255 |
| LMArena Chinese | 1215 | 1253 |
| LMArena French | 1261 | 1273 |
| LMArena German | 1222 | 1266 |
| LMArena Japanese | 1132 | 1208 |
| LMArena Korean | 1140 | 1206 |
| LMArena Russian | 1234 | 1263 |
| LMArena Spanish | 1253 | 1283 |
Instruction Following Llama 3.1-70B leads
Llama 3.1-70B: 65.3 (#223), Mistral Small 3.1: 63.6 (#230)
| Benchmark | Llama 3.1-70B | Mistral Small 3.1 |
|---|---|---|
| IFEval | 82.1% | 75% |
| LMArena Instruction Following | 1231 | 1264 |
Long Context Mistral Small 3.1 leads
Llama 3.1-70B: 37.6 (#214), Mistral Small 3.1: 39.5 (#178)
| Benchmark | Llama 3.1-70B | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1241 | 1299 |
Writing & Preference Mistral Small 3.1 leads
Llama 3.1-70B: 35.4 (#267), Mistral Small 3.1: 37.0 (#259)
| Benchmark | Llama 3.1-70B | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1261 | 1277 |
| LMArena Creative Writing | 1232 | 1253 |
| EQ-Bench Creative Writing | 784 | 761 |
| WildBench | 75.8% | 78.8% |
| LMArena Multi-Turn | 1256 | 1270 |
Frequently asked questions
Is Llama 3.1-70B better than Mistral Small 3.1?
Mistral Small 3.1 is the stronger model overall, scoring 31.7 to 29.6 on the Noometry Index.
Which is cheaper, Llama 3.1-70B or Mistral Small 3.1?
Llama 3.1-70B is cheaper. It lists at $0.40 per million input tokens and $0.40 per million output tokens; Mistral Small 3.1 lists at $0.35 and $0.56.
Is Llama 3.1-70B or Mistral Small 3.1 better for coding?
Mistral Small 3.1 scores higher on coding benchmarks: 38.3 versus 30.3 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Llama 3.1-70B and Mistral Small 3.1 share?
26 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Mistral Small 3.1 has 28.