Compare · ModelsLive · 2 picked · head to head

Qwen2.5-Max vs Claude Haiku 4.5

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

Winner summary

Claude Haiku 4.5 wins 4 of 4 shared benchmarks. Leads in math · knowledge.

Category leads
math·Claude Haiku 4.5knowledge·Claude Haiku 4.5
Hype vs Reality
Qwen2.5-Max
#141 by perf·no signal
QUIET
Claude Haiku 4.5
#161 by perf·no signal
QUIET
Best value
Qwen2.5-Max
no price
Claude Haiku 4.5
12.4 pts/$
$3.00/M
Vendor risk
Alibaba Qwen logo
Alibaba (Qwen)
$293.0B·Tier 1
Low risk
Anthropic logo
Anthropic
$380.0B·Tier 1
Medium risk
Head to head
Qwen2.5-MaxClaude Haiku 4.5
FrontierMath-2025-02-28-Private
Claude Haiku 4.5 leads by +4.9
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
Qwen2.5-Max
1.0
Claude Haiku 4.5
5.9
GPQA diamond
Claude Haiku 4.5 leads by +20.1
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Qwen2.5-Max
41.5
Claude Haiku 4.5
61.6
MATH level 5
Claude Haiku 4.5 leads by +29.2
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Qwen2.5-Max
67.2
Claude Haiku 4.5
96.4
OTIS Mock AIME 2024-2025
Claude Haiku 4.5 leads by +50.6
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Qwen2.5-Max
16.0
Claude Haiku 4.5
66.6
Full benchmark table
BenchmarkQwen2.5-MaxClaude Haiku 4.5
FrontierMath-2025-02-28-Private
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
1.05.9
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
41.561.6
MATH level 5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
67.296.4
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
16.066.6
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
Alibaba Qwen logoQwen2.5-Max
Anthropic logoClaude Haiku 4.5$1.00$5.00200K tokens (~100 books)$20.00