Compare/Llama 3.1 Instruct 405B vs Mistral Large 2 (Nov '24)

Llama 3.1 Instruct 405BvsMistral Large 2 (Nov '24)

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

Meta

Llama 3.1 Instruct 405B

Input
$2.75/M
Output
$6.5/M
Speed
38 tok/s
TTFT
0.67s
Mistral

Mistral Large 2 (Nov '24)

Input
$2/M
Output
$6/M
Speed
30 tok/s
TTFT
1.08s

Winner by Category

Cheaper
Mistral Large 2 (Nov '24)
Faster (tok/s)
Llama 3.1 Instruct 405B
Lower Latency
Llama 3.1 Instruct 405B
Benchmarks (9-3)
Llama 3.1 Instruct 405B

Pricing Comparison

MetricLlama 3.1 Instruct 405BMistral Large 2 (Nov '24)
Input ($/M tokens)$2.75$2
Output ($/M tokens)$6.5$6
Cost for 1M input + 100K output tokens:
Llama 3.1 Instruct 405B$3.40
Mistral Large 2 (Nov '24)$2.60

Speed Comparison

Output Speed (tokens/s) — higher is better
Llama 3.1 Instruct 405B
38 tok/s
Mistral Large 2 (Nov '24)
30 tok/s
Time to First Token (seconds) — lower is better
Llama 3.1 Instruct 405B
0.67s
Mistral Large 2 (Nov '24)
1.08s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
17.415.1
Coding Index
14.513.8
Math Index
3.014.0
GPQA Diamond
51.5%48.6%
MMLU-Pro
73.2%69.7%
LiveCodeBench
30.5%29.3%
AIME 2025
3.0%14.0%
MATH-500
70.3%73.6%
Humanity's Last Exam
4.2%4.0%
SciCode
29.9%29.2%
IFBench
39.0%31.2%
TerminalBench
6.8%6.1%
Llama 3.1 Instruct 405B9 wins
3 winsMistral Large 2 (Nov '24)

Frequently Asked Questions

Which is cheaper, Llama 3.1 Instruct 405B or Mistral Large 2 (Nov '24)?

Mistral Large 2 (Nov '24) is cheaper overall. Its blended price (3:1 input/output ratio) is $3.00/M tokens vs $3.69/M for Llama 3.1 Instruct 405B.

Which model performs better on benchmarks?

Llama 3.1 Instruct 405B wins 9 out of 12 benchmarks compared to 3 for Mistral Large 2 (Nov '24). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Llama 3.1 Instruct 405B generates tokens faster at 38 tok/s vs 30 tok/s. Llama 3.1 Instruct 405B also has lower time-to-first-token (0.67s vs 1.08s).

When should I use Llama 3.1 Instruct 405B vs Mistral Large 2 (Nov '24)?

Choose based on your priorities: Mistral Large 2 (Nov '24) for lower cost, Llama 3.1 Instruct 405B for stronger benchmark performance, and Llama 3.1 Instruct 405B for faster generation. For latency-sensitive apps, check the TTFT comparison above.