Compare · ModelsLive · 2 picked · head to head

GPT-5 vs Qwen2.5 72B Instruct

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

Winner summary

GPT-5 wins 5 of 5 shared benchmarks. Leads in knowledge · math.

Category leads
knowledge·GPT-5math·GPT-5
Hype vs Reality
GPT-5
#74 by perf·no signal
QUIET
Qwen2.5 72B Instruct
#82 by perf·no signal
QUIET
Best value
14.5x better value than GPT-5
GPT-5
9.7 pts/$
$5.63/M
Qwen2.5 72B Instruct
140.0 pts/$
$0.38/M
Vendor risk
OpenAI logo
OpenAI
$840.0B·Tier 1
Medium risk
Alibaba Qwen logo
Alibaba (Qwen)
$293.0B·Tier 1
Low risk
Head to head
GPT-5Qwen2.5 72B Instruct
Balrog
GPT-5 leads by +16.6
Balrog · benchmarks AI agents on text-based adventure games, testing language understanding, strategic planning, and long-horizon reasoning.
GPT-5
32.8
Qwen2.5 72B Instruct
16.2
GeoBench
GPT-5 leads by +19.0
GeoBench · tests geographic knowledge and spatial reasoning across countries, landmarks, coordinates, and geopolitical understanding.
GPT-5
81.0
Qwen2.5 72B Instruct
62.0
GPQA diamond
GPT-5 leads by +49.4
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-5
81.6
Qwen2.5 72B Instruct
32.2
MATH level 5
GPT-5 leads by +35.0
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
GPT-5
98.1
Qwen2.5 72B Instruct
63.2
OTIS Mock AIME 2024-2025
GPT-5 leads by +83.4
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-5
91.4
Qwen2.5 72B Instruct
8.0
Full benchmark table
BenchmarkGPT-5Qwen2.5 72B Instruct
Balrog
Balrog · benchmarks AI agents on text-based adventure games, testing language understanding, strategic planning, and long-horizon reasoning.
32.816.2
GeoBench
GeoBench · tests geographic knowledge and spatial reasoning across countries, landmarks, coordinates, and geopolitical understanding.
81.062.0
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
81.632.2
MATH level 5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
98.163.2
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
91.48.0
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
OpenAI logoGPT-5$1.25$10.00400K tokens (~200 books)$34.38
Alibaba Qwen logoQwen2.5 72B Instruct$0.36$0.4033K tokens (~16 books)$3.70