Model comparison
Llama 3-8B vs Pixtral Large
Pixtral Large is the stronger model overall, scoring 31.7 to 25.3 on the Noometry Index. Llama 3-8B costs 21× less per token, which makes it the better buy when Pixtral Large's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Meta
Mistral AISummary
- The widest gap is in reasoning, where Pixtral Large leads 20.9 to 13.8.
- Llama 3-8B is cheaper at $0.14 / $0.14 per million input/output tokens, against $2 / $6 for Pixtral Large.
- Pixtral Large accepts more context: 128K tokens versus 8K.
Side by side
| Llama 3-8B | Pixtral Large | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 25.3 | 31.7 |
| Released | 2024-04-18 | 2024-11-01 |
| Weights | Open | Open |
| Context window | 8K | 128K |
| Max output | 8K | 128K |
| Input $ / M tokens | $0.14 | $2 |
| Output $ / M tokens | $0.14 | $6 |
| Results tracked | 34 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3-8B: 30.5 (#285), Pixtral Large: —
| Benchmark | Llama 3-8B | Pixtral Large |
|---|---|---|
| BigCodeBench Instruct | 31.9% | — |
| LMArena Coding | 1152 | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Pixtral Large leads
Llama 3-8B: 13.8 (#321), Pixtral Large: 20.9 (#208)
| Benchmark | Llama 3-8B | Pixtral Large |
|---|---|---|
| Chess Puzzles | 0% | — |
| EnigmaEval | — | 0.8% |
| LMArena Hard Prompts | 1133 | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.33 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Not comparable
Llama 3-8B: 8.3 (#317), Pixtral Large: —
| Benchmark | Llama 3-8B | Pixtral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| LMArena Math | 1151 | — |
| MATH Level 5 | 6.1% | — |
Knowledge Not comparable
Llama 3-8B: 7.8 (#303), Pixtral Large: —
| Benchmark | Llama 3-8B | Pixtral Large |
|---|---|---|
| GPQA Diamond | 26.1% | — |
| LMArena Expert | 1113 | — |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multimodal Not comparable
Llama 3-8B: —, Pixtral Large: 30.0 (#105)
| Benchmark | Llama 3-8B | Pixtral Large |
|---|---|---|
| LMArena Vision | — | 1089 |
Multilingual Not comparable
Llama 3-8B: 31.0 (#256), Pixtral Large: —
| Benchmark | Llama 3-8B | Pixtral Large |
|---|---|---|
| LMArena Non-English | 1098 | — |
| LMArena Chinese | 1076 | — |
| LMArena French | 1158 | — |
| LMArena German | 1104 | — |
| LMArena Japanese | 967 | — |
| LMArena Korean | 1003 | — |
| LMArena Russian | 1109 | — |
| LMArena Spanish | 1172 | — |
Instruction Following Not comparable
Llama 3-8B: 58.7 (#255), Pixtral Large: —
| Benchmark | Llama 3-8B | Pixtral Large |
|---|---|---|
| LMArena Instruction Following | 1127 | — |
Long Context Not comparable
Llama 3-8B: 34.2 (#246), Pixtral Large: —
| Benchmark | Llama 3-8B | Pixtral Large |
|---|---|---|
| LMArena Longer Query | 1128 | — |
Writing & Preference Llama 3-8B leads
Llama 3-8B: 37.7 (#251), Pixtral Large: 32.9 (#273)
| Benchmark | Llama 3-8B | Pixtral Large |
|---|---|---|
| LMArena Text | 1166 | — |
| LMArena Creative Writing | 1150 | — |
| EQ-Bench Creative Writing | — | 988 |
| LMArena Multi-Turn | 1152 | — |
Frequently asked questions
Is Llama 3-8B better than Pixtral Large?
Pixtral Large is the stronger model overall, scoring 31.7 to 25.3 on the Noometry Index. Llama 3-8B costs 21× less per token, which makes it the better buy when Pixtral Large's lead doesn't matter for your workload.
Which is cheaper, Llama 3-8B or Pixtral Large?
Llama 3-8B is cheaper. It lists at $0.14 per million input tokens and $0.14 per million output tokens; Pixtral Large lists at $2 and $6.
Which has the bigger context window?
Pixtral Large does, with 128K tokens against 8K.
How many benchmarks do Llama 3-8B and Pixtral Large share?
0 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Pixtral Large has 3.