Compare · ModelsLive · 2 picked · head to head

Qwen2.5 Coder 14B Instruct vs Qwen2.5 72B Instruct

Side by side · benchmarks, pricing, and signals you can act on.

Winner summary

Qwen2.5 72B Instruct wins 10 of 11 shared benchmarks. Leads in knowledge · general · language.

Category leads
coding·Qwen2.5 Coder 14B Instructknowledge·Qwen2.5 72B Instructgeneral·Qwen2.5 72B Instructlanguage·Qwen2.5 72B Instructmath·Qwen2.5 72B Instructreasoning·Qwen2.5 72B Instruct
Hype vs Reality
Qwen2.5 Coder 14B Instruct
#120 by perf·no signal
QUIET
Qwen2.5 72B Instruct
#107 by perf·no signal
QUIET
Best value
Qwen2.5 Coder 14B Instruct
no price
Qwen2.5 72B Instruct
135.8 pts/$
$0.38/M
Vendor risk
Alibaba logo
Alibaba (Qwen)
$293.0B·Tier 1
Low risk
Alibaba Qwen logo
Alibaba (Qwen)
$293.0B·Tier 1
Low risk
Head to head
Qwen2.5 Coder 14B InstructQwen2.5 72B Instruct
Aider · Code Editing
Qwen2.5 Coder 14B Instruct leads by +3.8
Qwen2.5 Coder 14B Instruct
69.2
Qwen2.5 72B Instruct
65.4
ARC AI2
Qwen2.5 72B Instruct leads by +38.0
AI2 Reasoning Challenge · tests grade-school level science knowledge with multiple-choice questions requiring reasoning beyond simple retrieval.
Qwen2.5 Coder 14B Instruct
54.7
Qwen2.5 72B Instruct
92.7
HellaSwag
Qwen2.5 72B Instruct leads by +6.1
HellaSwag · tests commonsense reasoning by asking models to predict the most plausible continuation of everyday scenarios.
Qwen2.5 Coder 14B Instruct
73.6
Qwen2.5 72B Instruct
79.7
BBH (HuggingFace)
Qwen2.5 72B Instruct leads by +17.6
Qwen2.5 Coder 14B Instruct
44.2
Qwen2.5 72B Instruct
61.9
GPQA
Qwen2.5 72B Instruct leads by +9.4
Qwen2.5 Coder 14B Instruct
7.3
Qwen2.5 72B Instruct
16.7
IFEval
Qwen2.5 72B Instruct leads by +17.3
Qwen2.5 Coder 14B Instruct
69.1
Qwen2.5 72B Instruct
86.4
MATH Level 5
Qwen2.5 72B Instruct leads by +27.3
Qwen2.5 Coder 14B Instruct
32.5
Qwen2.5 72B Instruct
59.8
MMLU-PRO
Qwen2.5 72B Instruct leads by +18.7
Qwen2.5 Coder 14B Instruct
32.7
Qwen2.5 72B Instruct
51.4
MUSR
Qwen2.5 72B Instruct leads by +4.7
Qwen2.5 Coder 14B Instruct
7.0
Qwen2.5 72B Instruct
11.7
MMLU
Qwen2.5 72B Instruct leads by +13.5
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
Qwen2.5 Coder 14B Instruct
66.9
Qwen2.5 72B Instruct
80.4
Winogrande
Qwen2.5 72B Instruct leads by +11.0
WinoGrande · large-scale commonsense reasoning benchmark where models must resolve ambiguous pronouns in carefully constructed sentence pairs.
Qwen2.5 Coder 14B Instruct
53.6
Qwen2.5 72B Instruct
64.6
Full benchmark table
BenchmarkQwen2.5 Coder 14B InstructQwen2.5 72B Instruct
Aider · Code Editing
69.265.4
ARC AI2
AI2 Reasoning Challenge · tests grade-school level science knowledge with multiple-choice questions requiring reasoning beyond simple retrieval.
54.792.7
HellaSwag
HellaSwag · tests commonsense reasoning by asking models to predict the most plausible continuation of everyday scenarios.
73.679.7
BBH (HuggingFace)
44.261.9
GPQA
7.316.7
IFEval
69.186.4
MATH Level 5
32.559.8
MMLU-PRO
32.751.4
MUSR
7.011.7
MMLU
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
66.980.4
Winogrande
WinoGrande · large-scale commonsense reasoning benchmark where models must resolve ambiguous pronouns in carefully constructed sentence pairs.
53.664.6
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
Alibaba logoQwen2.5 Coder 14B Instruct
Alibaba Qwen logoQwen2.5 72B Instruct$0.36$0.40131K tokens (~66 books)$3.70