token.app › Compare › Qwen2.5 72B Instruct vs Kimi K3

Qwen2.5 72B Instruct vs Kimi K3

Kimi K3 leads on 2 of 2 shared benchmarks. Qwen2.5 72B Instruct is 16× cheaper per token on a blended 3:1 basis. Kimi K3 accepts the larger context window (1.0M).

Head to head
Blended price uses a 3:1 input:output mix
Qwen2.5 72B InstructKimi K3
ProviderAlibabaMoonshot AI
Input $/1M$0.360$3.00
Output $/1M$0.400$15.00
Blended $/1M$0.370$6.00
Context window33K1.0M
Max output16K—
ReleasedSep 2024Jul 2026
LicenceOpen weightsOpen weights
GPQA Diamond 49.1% 93.1%
OTIS Mock AIME 8.1% 97.2%
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Qwen2.5 72B Instruct if…
  • Costs less per token — $0.370 vs $6.00 blended
Choose Kimi K3 if…
  • Higher GPQA Diamond (93.1% vs 49.1%)
  • Higher OTIS Mock AIME (97.2% vs 8.1%)
  • Larger context window (1.0M)
  • Newer model (released Jul 2026)
FAQ
Which is better, Qwen2.5 72B Instruct or Kimi K3?
Across the 2 benchmarks both models have independently-run scores for, Qwen2.5 72B Instruct leads on 0 and Kimi K3 leads on 2. Benchmarks are one input — price and context window are on this page too.
Is Qwen2.5 72B Instruct cheaper than Kimi K3?
Qwen2.5 72B Instruct is cheaper: $0.370 versus $6.00 per million tokens blended at 3:1 input:output. Input alone: $0.360 vs $3.00. Output alone: $0.400 vs $15.00.
What context windows do Qwen2.5 72B Instruct and Kimi K3 have?
Qwen2.5 72B Instruct: 32,768 tokens. Kimi K3: 1,048,576 tokens.
Who makes Qwen2.5 72B Instruct and Kimi K3?
Qwen2.5 72B Instruct is made by Alibaba. Kimi K3 is made by Moonshot AI.
Related comparisons
Qwen2.5 72B Instruct full details Kimi K3 full details Qwen2.5 72B Instruct vs Ling 3.0 Tiny (free) Qwen2.5 72B Instruct vs Muse Spark 1.2 Qwen2.5 72B Instruct vs Qwen3.8 Max Qwen2.5 72B Instruct vs DeepSeek V4 Flash Latest Qwen2.5 72B Instruct vs DeepSeek V4 Flash 0731 Qwen2.5 72B Instruct vs Inkling Small