Model comparison
Llama 3.1-8B vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 39.1 to 23.0 on the Noometry Index. Llama 3.1-8B costs 6.5× 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 3.1-8B scores higher in 0 categories and Mistral Large 3 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Large 3 leads 60.0 to 29.7.
- Llama 3.1-8B is cheaper at $0.05 / $0.08 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 3.1-8B | Mistral Large 3 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 23.0 | 39.1 |
| Released | 2024-07-23 | 2025-12-02 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 8K |
| Input $ / M tokens | $0.05 | $0.25 |
| Output $ / M tokens | $0.08 | $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 3.1-8B: 20.2 (#340), Mistral Large 3: 34.4 (#237)
| Benchmark | Llama 3.1-8B | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1195 | 1448 |
| LMArena WebDev | — | 1230 |
| SciCode | 13.2% | — |
| WeirdML | 1.7% | — |
| BigCodeBench Instruct | 32.8% | — |
| BigCodeBench Complete | 40.5% | — |
| HumanEval+ | 62.8% | — |
| MBPP+ | 55.6% | — |
Agentic & Tool Use Not comparable
Llama 3.1-8B: 22.5 (#131), Mistral Large 3: —
| Benchmark | Llama 3.1-8B | Mistral Large 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25.8% | — |
| BALROG | 15.1% | — |
Reasoning Too close to call
Llama 3.1-8B: 14.9 (#321), Mistral Large 3: 15.2 (#319)
| Benchmark | Llama 3.1-8B | Mistral Large 3 |
|---|---|---|
| LMArena Hard Prompts | 1175 | 1429 |
| Kagi LLM Benchmark | — | 50.9% |
| NYT Connections (extended) | — | 7.5% |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 23% |
| DTBench | 50.9% | — |
| LMCA | 5.4% | — |
| Epoch Capabilities Index | 116.57 | — |
| PIQA | 81.2% | — |
Math Mistral Large 3 leads
Llama 3.1-8B: 10.2 (#317), Mistral Large 3: 38.7 (#129)
| Benchmark | Llama 3.1-8B | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1179 | 1414 |
| OTIS Mock AIME 2024-2025 | 1.7% | — |
| Omni-MATH | 13.7% | — |
| MATH Level 5 | 22.9% | — |
| GSM8K | 82.4% | — |
Knowledge Mistral Large 3 leads
Llama 3.1-8B: 8.0 (#307), Mistral Large 3: 36.0 (#177)
| Benchmark | Llama 3.1-8B | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1144 | 1421 |
| GPQA Diamond | 27% | — |
| MMLU-Pro | 40.6% | — |
| Vectara Hallucination Rate | — | 14.5% |
| GPQA (HELM) | 24.7% | — |
| BoolQ | 82.8% | — |
| MMLU | 56.1% | — |
Multimodal Not comparable
Llama 3.1-8B: —, Mistral Large 3: 38.2 (#66)
| Benchmark | Llama 3.1-8B | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1221 |
Multilingual Mistral Large 3 leads
Llama 3.1-8B: 34.0 (#249), Mistral Large 3: 52.5 (#84)
| Benchmark | Llama 3.1-8B | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1148 | 1413 |
| LMArena Chinese | 1151 | 1447 |
| LMArena French | 1177 | 1455 |
| LMArena German | 1144 | 1437 |
| LMArena Japanese | 1061 | 1394 |
| LMArena Korean | 1053 | 1384 |
| LMArena Russian | 1158 | 1411 |
| LMArena Spanish | 1169 | 1440 |
Instruction Following Mistral Large 3 leads
Llama 3.1-8B: 58.9 (#258), Mistral Large 3: 74.0 (#108)
| Benchmark | Llama 3.1-8B | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1159 | 1403 |
| IFEval | 74.3% | — |
Long Context Mistral Large 3 leads
Llama 3.1-8B: 35.8 (#238), Mistral Large 3: 43.1 (#105)
| Benchmark | Llama 3.1-8B | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1182 | 1413 |
Writing & Preference Mistral Large 3 leads
Llama 3.1-8B: 29.7 (#290), Mistral Large 3: 60.0 (#101)
| Benchmark | Llama 3.1-8B | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1187 | 1428 |
| LMArena Creative Writing | 1154 | 1386 |
| EQ-Bench Creative Writing | 713 | 1412 |
| LMArena Multi-Turn | 1172 | 1429 |
| WildBench | 68.7% | — |
Frequently asked questions
Is Llama 3.1-8B better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 23.0 on the Noometry Index. Llama 3.1-8B costs 6.5× 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 3.1-8B or Mistral Large 3?
Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Mistral Large 3 lists at $0.25 and $0.75.
Is Llama 3.1-8B or Mistral Large 3 better for coding?
Mistral Large 3 scores higher on coding benchmarks: 34.4 versus 20.2 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 3.1-8B and Mistral Large 3 share?
18 benchmarks have published results for both models. Llama 3.1-8B has 43 scored results on Noometry and Mistral Large 3 has 24.