Compare/Qwen3 235B A22B (Non-reasoning) vs MiMo-V2.5

Qwen3 235B A22B (Non-reasoning)vsMiMo-V2.5

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

Alibaba

Qwen3 235B A22B (Non-reasoning)

Input
$0.45/M
Output
$1.8/M
Speed
68 tok/s
TTFT
1.23s
Xiaomi

MiMo-V2.5

Input
$0.36/M
Output
$1.8/M
Speed
88 tok/s
TTFT
2.03s

Winner by Category

Cheaper
MiMo-V2.5
Faster (tok/s)
MiMo-V2.5
Lower Latency
Qwen3 235B A22B (Non-reasoning)
Benchmarks (5-7)
MiMo-V2.5

Pricing Comparison

MetricQwen3 235B A22B (Non-reasoning)MiMo-V2.5
Input ($/M tokens)$0.45$0.36
Output ($/M tokens)$1.8$1.8
Cost for 1M input + 100K output tokens:
Qwen3 235B A22B (Non-reasoning)$0.63
MiMo-V2.5$0.54

Speed Comparison

Output Speed (tokens/s) — higher is better
Qwen3 235B A22B (Non-reasoning)
68 tok/s
MiMo-V2.5
88 tok/s
Time to First Token (seconds) — lower is better
Qwen3 235B A22B (Non-reasoning)
1.23s
MiMo-V2.5
2.03s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
17.049.0
Coding Index
14.042.1
Math Index
23.7
GPQA Diamond
61.3%84.9%
MMLU-Pro
76.2%
LiveCodeBench
34.3%
AIME 2025
23.7%
MATH-500
90.2%
Humanity's Last Exam
4.7%25.2%
SciCode
29.9%43.1%
IFBench
36.6%67.1%
TerminalBench
6.1%41.7%
Qwen3 235B A22B (Non-reasoning)5 wins
7 winsMiMo-V2.5

Frequently Asked Questions

Which is cheaper, Qwen3 235B A22B (Non-reasoning) or MiMo-V2.5?

MiMo-V2.5 is cheaper overall. Its blended price (3:1 input/output ratio) is $0.72/M tokens vs $0.79/M for Qwen3 235B A22B (Non-reasoning).

Which model performs better on benchmarks?

MiMo-V2.5 wins 7 out of 12 benchmarks compared to 5 for Qwen3 235B A22B (Non-reasoning). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

MiMo-V2.5 generates tokens faster at 88 tok/s vs 68 tok/s. Qwen3 235B A22B (Non-reasoning) also has lower time-to-first-token (1.23s vs 2.03s).

When should I use Qwen3 235B A22B (Non-reasoning) vs MiMo-V2.5?

Choose based on your priorities: MiMo-V2.5 for lower cost, MiMo-V2.5 for stronger benchmark performance, and MiMo-V2.5 for faster generation. For latency-sensitive apps, check the TTFT comparison above.