Model comparison
Llama-3.3-70B-Instruct vs Mistral Small 3.1
Mistral Small 3.1 is the stronger model overall, scoring 31.4 to 30.3 on the Noometry Index. Llama-3.3-70B-Instruct costs 2.6× less per token, which makes it the better buy when Mistral Small 3.1's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Meta
Mistral AISummary
- They share 20 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 4 categories and Mistral Small 3.1 in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where Mistral Small 3.1 leads 39.5 to 26.4.
- The biggest single-benchmark swing is GPQA Diamond: 47.4% for Llama-3.3-70B-Instruct and 41.9% for Mistral Small 3.1.
- Llama-3.3-70B-Instruct is cheaper at $0.10 / $0.32 per million input/output tokens, against $0.35 / $0.56 for Mistral Small 3.1.
Side by side
| Llama-3.3-70B-Instruct | Mistral Small 3.1 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.3 | 31.4 |
| Released | 2024-12-06 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 128K | 128K |
| Max output | 4K | 102K |
| Input $ / M tokens | $0.10 | $0.35 |
| Output $ / M tokens | $0.32 | $0.56 |
| Results tracked | 43 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3.1 leads
Llama-3.3-70B-Instruct: 30.6 (#284), Mistral Small 3.1: 37.7 (#175)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1268 | 1309 |
| SciCode | 26% | — |
| WeirdML | 14.4% | — |
| BigCodeBench Instruct | 46.9% | — |
| LiveBench Coding | 36.6% | — |
| BigCodeBench Complete | 57.5% | — |
Agentic & Tool Use Not comparable
Llama-3.3-70B-Instruct: 25.6 (#100), Mistral Small 3.1: —
| Benchmark | Llama-3.3-70B-Instruct | Mistral Small 3.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 31.9% | — |
| BALROG | 23% | — |
Reasoning Mistral Small 3.1 leads
Llama-3.3-70B-Instruct: 13.7 (#325), Mistral Small 3.1: 18.9 (#249)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Small 3.1 |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1278 |
| Epoch Capabilities Index | 127.32 | 127.48 |
| SimpleBench | 19.9% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | 50.8% | — |
| DTBench | 59.5% | — |
| LiveBench Data Analysis | 49.5% | — |
| LMCA | 17.5% | — |
| ForecastBench | 58.6 | — |
| LiveBench | 50.2% | — |
Math Too close to call
Llama-3.3-70B-Instruct: 14.3 (#292), Mistral Small 3.1: 13.7 (#295)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Small 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.1% | 3.9% |
| LMArena Math | 1268 | 1261 |
| Omni-MATH | — | 24.8% |
| LiveBench Math | 42.2% | — |
| MATH Level 5 | 41.6% | — |
Knowledge Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 30.5 (#220), Mistral Small 3.1: 22.6 (#266)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Small 3.1 |
|---|---|---|
| GPQA Diamond | 47.4% | 41.9% |
| LMArena Expert | 1225 | 1258 |
| MMLU-Pro | — | 61% |
| Confabulations | 22.8% | — |
| Vectara Hallucination Rate | 4.1% | — |
| GPQA (HELM) | — | 39.2% |
| MMLU | 86.3% | — |
Multimodal Not comparable
Llama-3.3-70B-Instruct: —, Mistral Small 3.1: 32.6 (#93)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | — | 1136 |
Multilingual Mistral Small 3.1 leads
Llama-3.3-70B-Instruct: 40.1 (#215), Mistral Small 3.1: 41.4 (#204)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1236 | 1255 |
| LMArena Chinese | 1217 | 1254 |
| LMArena French | 1280 | 1270 |
| LMArena German | 1251 | 1266 |
| LMArena Japanese | 1149 | 1210 |
| LMArena Korean | 1142 | 1206 |
| LMArena Russian | 1252 | 1263 |
| LMArena Spanish | 1269 | 1283 |
Instruction Following Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 71.3 (#152), Mistral Small 3.1: 63.8 (#225)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Small 3.1 |
|---|---|---|
| LMArena Instruction Following | 1242 | 1264 |
| LiveBench Instruction Following | 82.7% | — |
| IFEval | — | 75% |
Long Context Mistral Small 3.1 leads
Llama-3.3-70B-Instruct: 26.4 (#290), Mistral Small 3.1: 39.5 (#172)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1256 | 1300 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 47.8 (#203), Mistral Small 3.1: 37.2 (#254)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1274 | 1278 |
| LMArena Creative Writing | 1250 | 1253 |
| LMArena Multi-Turn | 1279 | 1270 |
| EQ-Bench Creative Writing | — | 761 |
| WildBench | — | 78.8% |
| LiveBench Language | 39.2% | — |
Frequently asked questions
Is Llama-3.3-70B-Instruct better than Mistral Small 3.1?
Mistral Small 3.1 is the stronger model overall, scoring 31.4 to 30.3 on the Noometry Index. Llama-3.3-70B-Instruct costs 2.6× less per token, which makes it the better buy when Mistral Small 3.1's lead doesn't matter for your workload.
Which is cheaper, Llama-3.3-70B-Instruct or Mistral Small 3.1?
Llama-3.3-70B-Instruct is cheaper. It lists at $0.10 per million input tokens and $0.32 per million output tokens; Mistral Small 3.1 lists at $0.35 and $0.56.
Is Llama-3.3-70B-Instruct or Mistral Small 3.1 better for coding?
Mistral Small 3.1 scores higher on coding benchmarks: 37.7 versus 30.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Llama-3.3-70B-Instruct and Mistral Small 3.1 share?
20 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Mistral Small 3.1 has 28.