Model comparison
Llama 3-8B vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 38.6 to 25.3 on the Noometry Index. Llama 3-8B costs 2.7× less per token, which makes it the better buy when Mistral Large 3's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Meta
Mistral AISummary
- They share 17 benchmarks with published results for both. Llama 3-8B scores higher in 0 categories and Mistral Large 3 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Large 3 leads 36.0 to 8.3.
- Llama 3-8B is cheaper at $0.14 / $0.14 per million input/output tokens, against $0.25 / $0.75 for Mistral Large 3.
- Mistral Large 3 accepts more context: 262K tokens versus 8K.
Side by side
| Llama 3-8B | Mistral Large 3 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 25.3 | 38.6 |
| Released | 2024-04-18 | 2025-12-02 |
| Weights | Open | Open |
| Context window | 8K | 262K |
| Max output | 8K | 8K |
| Input $ / M tokens | $0.14 | $0.25 |
| Output $ / M tokens | $0.14 | $0.75 |
| Results tracked | 34 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 3 leads
Llama 3-8B: 30.5 (#285), Mistral Large 3: 34.1 (#230)
| Benchmark | Llama 3-8B | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1152 | 1447 |
| LMArena WebDev | — | 1230 |
| BigCodeBench Instruct | 31.9% | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Too close to call
Llama 3-8B: 13.8 (#321), Mistral Large 3: 14.6 (#314)
| Benchmark | Llama 3-8B | Mistral Large 3 |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1429 |
| Kagi LLM Benchmark | — | 50.9% |
| NYT Connections (extended) | — | 7.5% |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 23% |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.33 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Mistral Large 3 leads
Llama 3-8B: 8.3 (#317), Mistral Large 3: 36.0 (#131)
| Benchmark | Llama 3-8B | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1151 | 1415 |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| MATH Level 5 | 6.1% | — |
Knowledge Mistral Large 3 leads
Llama 3-8B: 7.8 (#303), Mistral Large 3: 35.5 (#173)
| Benchmark | Llama 3-8B | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1113 | 1421 |
| GPQA Diamond | 26.1% | — |
| Vectara Hallucination Rate | — | 14.5% |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multimodal Not comparable
Llama 3-8B: —, Mistral Large 3: 37.6 (#65)
| Benchmark | Llama 3-8B | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1222 |
Multilingual Mistral Large 3 leads
Llama 3-8B: 31.0 (#256), Mistral Large 3: 52.6 (#79)
| Benchmark | Llama 3-8B | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1098 | 1412 |
| LMArena Chinese | 1076 | 1448 |
| LMArena French | 1158 | 1456 |
| LMArena German | 1104 | 1438 |
| LMArena Japanese | 967 | 1399 |
| LMArena Korean | 1003 | 1384 |
| LMArena Russian | 1109 | 1412 |
| LMArena Spanish | 1172 | 1437 |
Instruction Following Mistral Large 3 leads
Llama 3-8B: 58.7 (#255), Mistral Large 3: 74.1 (#104)
| Benchmark | Llama 3-8B | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1127 | 1402 |
Long Context Mistral Large 3 leads
Llama 3-8B: 34.2 (#246), Mistral Large 3: 43.1 (#102)
| Benchmark | Llama 3-8B | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1128 | 1413 |
Writing & Preference Mistral Large 3 leads
Llama 3-8B: 37.7 (#251), Mistral Large 3: 60.2 (#100)
| Benchmark | Llama 3-8B | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1166 | 1427 |
| LMArena Creative Writing | 1150 | 1385 |
| LMArena Multi-Turn | 1152 | 1429 |
| EQ-Bench Creative Writing | — | 1412 |
Frequently asked questions
Is Llama 3-8B better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 38.6 to 25.3 on the Noometry Index. Llama 3-8B costs 2.7× 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 3-8B or Mistral Large 3?
Llama 3-8B is cheaper. It lists at $0.14 per million input tokens and $0.14 per million output tokens; Mistral Large 3 lists at $0.25 and $0.75.
Is Llama 3-8B or Mistral Large 3 better for coding?
Mistral Large 3 scores higher on coding benchmarks: 34.1 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 3 does, with 262K tokens against 8K.
How many benchmarks do Llama 3-8B and Mistral Large 3 share?
17 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Mistral Large 3 has 24.