Compare/Qwen2.5 Max vs Mistral Large 2 (Jul '24)

Qwen2.5 MaxvsMistral Large 2 (Jul '24)

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

Alibaba

Qwen2.5 Max

Input
$1.6/M
Output
$6.4/M
Speed
48 tok/s
TTFT
1.09s
Mistral

Mistral Large 2 (Jul '24)

Input
$2/M
Output
$6/M
Speed
TTFT

Winner by Category

Cheaper
Qwen2.5 Max
Faster (tok/s)
Qwen2.5 Max
Lower Latency
Mistral Large 2 (Jul '24)
Benchmarks (7-3)
Qwen2.5 Max

Pricing Comparison

MetricQwen2.5 MaxMistral Large 2 (Jul '24)
Input ($/M tokens)$1.6$2
Output ($/M tokens)$6.4$6
Cost for 1M input + 100K output tokens:
Qwen2.5 Max$2.24
Mistral Large 2 (Jul '24)$2.60

Speed Comparison

Output Speed (tokens/s) — higher is better
Qwen2.5 Max
48 tok/s
Mistral Large 2 (Jul '24)
Time to First Token (seconds) — lower is better
Qwen2.5 Max
1.09s
Mistral Large 2 (Jul '24)

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
16.313.0
Coding Index
Math Index
0.0
GPQA Diamond
58.7%47.2%
MMLU-Pro
76.2%68.3%
LiveCodeBench
35.9%26.7%
AIME 2025
0.0%
MATH-500
83.5%71.4%
Humanity's Last Exam
4.5%3.2%
SciCode
33.7%27.1%
IFBench
31.6%
TerminalBench
Qwen2.5 Max7 wins
3 winsMistral Large 2 (Jul '24)

Frequently Asked Questions

Which is cheaper, Qwen2.5 Max or Mistral Large 2 (Jul '24)?

Qwen2.5 Max is cheaper overall. Its blended price (3:1 input/output ratio) is $2.80/M tokens vs $3.00/M for Mistral Large 2 (Jul '24).

Which model performs better on benchmarks?

Qwen2.5 Max wins 7 out of 12 benchmarks compared to 3 for Mistral Large 2 (Jul '24). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Qwen2.5 Max generates tokens faster at 48 tok/s vs 0 tok/s. However, Mistral Large 2 (Jul '24) has lower time-to-first-token (0.00s vs 1.09s).

When should I use Qwen2.5 Max vs Mistral Large 2 (Jul '24)?

Choose based on your priorities: Qwen2.5 Max for lower cost, Qwen2.5 Max for stronger benchmark performance, and Qwen2.5 Max for faster generation. For latency-sensitive apps, check the TTFT comparison above.