Compare · ModelsLive · 2 picked · head to head
Qwen2-72B vs Kimi K2.5
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Kimi K2.5 wins on 2/2 benchmarks
Kimi K2.5 wins 2 of 2 shared benchmarks. Leads in knowledge · coding.
Category leads
knowledge·Kimi K2.5coding·Kimi K2.5
Hype vs Reality
Attention vs performance
Qwen2-72B
#177 by perf·no signal
Kimi K2.5
#104 by perf·no signal
Vendor risk
Who is behind the model
Alibaba (Qwen)
$293.0B·Tier 1
moonshotai
private · undisclosed
Head to head
2 benchmarks · 2 models
Qwen2-72BKimi K2.5
GPQA diamond
Kimi K2.5 leads by +62.4
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Qwen2-72B
21.0
Kimi K2.5
83.5
WeirdML
Kimi K2.5 leads by +34.3
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Qwen2-72B
11.3
Kimi K2.5
45.6
Full benchmark table
| Benchmark | Qwen2-72B | Kimi K2.5 |
|---|---|---|
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 21.0 | 83.5 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 11.3 | 45.6 |
Pricing · per 1M tokens · projected $/mo at 10M tokens