Model comparison
Llama-3.3-70B-Instruct vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 39.1 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 2.4× less per token, which makes it the better buy when Mistral Large 3's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Meta
Mistral AISummary
- They share 18 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 0 categories and Mistral Large 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Large 3 leads 38.7 to 15.3.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 4.1% for Llama-3.3-70B-Instruct and 14.5% for Mistral Large 3.
- Llama-3.3-70B-Instruct is cheaper at $0.10 / $0.32 per million input/output tokens, against $0.25 / $0.75 for Mistral Large 3.
- Mistral Large 3 accepts more context: 262K tokens versus 128K.
Side by side
| Llama-3.3-70B-Instruct | Mistral Large 3 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.6 | 39.1 |
| Released | 2024-12-06 | 2025-12-02 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 8K |
| Input $ / M tokens | $0.10 | $0.25 |
| Output $ / M tokens | $0.32 | $0.75 |
| Results tracked | 43 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 3 leads
Llama-3.3-70B-Instruct: 31.0 (#290), Mistral Large 3: 34.4 (#237)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1268 | 1448 |
| LMArena WebDev | — | 1230 |
| 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: 25.8 (#105), Mistral Large 3: —
| Benchmark | Llama-3.3-70B-Instruct | Mistral Large 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 31.9% | — |
| BALROG | 23% | — |
Reasoning Mistral Large 3 leads
Llama-3.3-70B-Instruct: 14.1 (#327), Mistral Large 3: 15.2 (#319)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1429 |
| SimpleBench | 19.9% | — |
| Kagi LLM Benchmark | — | 50.9% |
| NYT Connections (extended) | — | 7.5% |
| CritPt | 0% | — |
| Thematic Generalization | — | 23% |
| LiveBench Reasoning | 50.8% | — |
| DTBench | 59.5% | — |
| LiveBench Data Analysis | 49.5% | — |
| LMCA | 17.5% | — |
| Epoch Capabilities Index | 127.33 | — |
| ForecastBench | 58.6 | — |
| LiveBench | 50.2% | — |
Math Mistral Large 3 leads
Llama-3.3-70B-Instruct: 15.3 (#298), Mistral Large 3: 38.7 (#129)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1267 | 1414 |
| OTIS Mock AIME 2024-2025 | 5.1% | — |
| LiveBench Math | 42.2% | — |
| MATH Level 5 | 41.6% | — |
Knowledge Mistral Large 3 leads
Llama-3.3-70B-Instruct: 30.6 (#226), Mistral Large 3: 36.0 (#177)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Large 3 |
|---|---|---|
| Vectara Hallucination Rate | 4.1% | 14.5% |
| LMArena Expert | 1225 | 1421 |
| GPQA Diamond | 47.4% | — |
| Confabulations | 22.8% | — |
| MMLU | 86.3% | — |
Multimodal Not comparable
Llama-3.3-70B-Instruct: —, Mistral Large 3: 38.2 (#66)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1221 |
Multilingual Mistral Large 3 leads
Llama-3.3-70B-Instruct: 39.9 (#220), Mistral Large 3: 52.5 (#84)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1236 | 1413 |
| LMArena Chinese | 1217 | 1447 |
| LMArena French | 1281 | 1455 |
| LMArena German | 1251 | 1437 |
| LMArena Japanese | 1150 | 1394 |
| LMArena Korean | 1143 | 1384 |
| LMArena Russian | 1252 | 1411 |
| LMArena Spanish | 1270 | 1440 |
Instruction Following Mistral Large 3 leads
Llama-3.3-70B-Instruct: 71.1 (#157), Mistral Large 3: 74.0 (#108)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1242 | 1403 |
| LiveBench Instruction Following | 82.7% | — |
Long Context Mistral Large 3 leads
Llama-3.3-70B-Instruct: 26.4 (#295), Mistral Large 3: 43.1 (#105)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1256 | 1413 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Mistral Large 3 leads
Llama-3.3-70B-Instruct: 47.6 (#207), Mistral Large 3: 60.0 (#101)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1274 | 1428 |
| LMArena Creative Writing | 1250 | 1386 |
| LMArena Multi-Turn | 1280 | 1429 |
| EQ-Bench Creative Writing | — | 1412 |
| LiveBench Language | 39.2% | — |
Frequently asked questions
Is Llama-3.3-70B-Instruct better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 2.4× less per token, which makes it the better buy when Mistral Large 3's lead doesn't matter for your workload.
Which is cheaper, Llama-3.3-70B-Instruct or Mistral Large 3?
Llama-3.3-70B-Instruct is cheaper. It lists at $0.10 per million input tokens and $0.32 per million output tokens; Mistral Large 3 lists at $0.25 and $0.75.
Is Llama-3.3-70B-Instruct or Mistral Large 3 better for coding?
Mistral Large 3 scores higher on coding benchmarks: 34.4 versus 31.0 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 3 does, with 262K tokens against 128K.
How many benchmarks do Llama-3.3-70B-Instruct and Mistral Large 3 share?
18 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Mistral Large 3 has 24.