Compare · ModelsLive · 2 picked · head to head
Llama 3.1 8B Instruct vs Mistral Large
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Mistral Large wins on 6/6 benchmarks
Mistral Large wins 6 of 6 shared benchmarks. Leads in coding · general · knowledge.
Category leads
coding·Mistral Largegeneral·Mistral Largeknowledge·Mistral Largemath·Mistral Large
Hype vs Reality
Attention vs performance
Llama 3.1 8B Instruct
#289 by perf·#19 by attention
Mistral Large
#196 by perf·#18 by attention
Best value
Llama 3.1 8B Instruct
79.4x better value than Mistral Large
Llama 3.1 8B Instruct
810.0 pts/$
$0.03/M
Mistral Large
10.2 pts/$
$4.00/M
Vendor risk
Who is behind the model
Meta AI
$1.65T·Tier 1
Mistral AI
$24.0B·Tier 1
Head to head
6 benchmarks · 2 models
Llama 3.1 8B InstructMistral Large
Aider · Code Editing
Mistral Large leads by +27.8
Llama 3.1 8B Instruct
37.6
Mistral Large
65.4
Dtbench
Mistral Large leads by +8.3
Llama 3.1 8B Instruct
18.2
Mistral Large
26.5
GPQA diamond
Mistral Large leads by +16.4
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Llama 3.1 8B Instruct
2.7
Mistral Large
19.1
MATH level 5
Mistral Large leads by +1.6
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Llama 3.1 8B Instruct
22.9
Mistral Large
24.5
MMLU
Mistral Large leads by +16.9
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
Llama 3.1 8B Instruct
41.5
Mistral Large
58.4
OTIS Mock AIME 2024-2025
Mistral Large leads by +0.3
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Llama 3.1 8B Instruct
1.6
Mistral Large
1.9
Full benchmark table
| Benchmark | Llama 3.1 8B Instruct | Mistral Large |
|---|---|---|
Aider · Code Editing | 37.6 | 65.4 |
Dtbench | 18.2 | 26.5 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 2.7 | 19.1 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 22.9 | 24.5 |
MMLU Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge. | 41.5 | 58.4 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 1.6 | 1.9 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.02 | $0.04 | 131K tokens (~66 books) | $0.25 | |
| $2.00 | $6.00 | 128K tokens (~64 books) | $30.00 |