Compare · ModelsLive · 2 picked · head to head

Qwen2.5-Max vs Mistral Large 2411

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

Winner summary

Qwen2.5-Max wins 5 of 5 shared benchmarks. Leads in arena · math · knowledge.

Category leads
arena·Qwen2.5-Maxmath·Qwen2.5-Maxknowledge·Qwen2.5-Max
Hype vs Reality
Qwen2.5-Max
#141 by perf·no signal
QUIET
Mistral Large 2411
#112 by perf·no signal
QUIET
Best value
Qwen2.5-Max
no price
Mistral Large 2411
11.4 pts/$
$4.00/M
Vendor risk
Alibaba Qwen logo
Alibaba (Qwen)
$293.0B·Tier 1
Low risk
Mistral AI logo
Mistral AI
$14.0B·Tier 1
Medium risk
Head to head
Qwen2.5-MaxMistral Large 2411
Chatbot Arena Elo · Overall
Qwen2.5-Max leads by +69.5
Qwen2.5-Max
1374.2
Mistral Large 2411
1304.7
FrontierMath-2025-02-28-Private
Qwen2.5-Max leads by +0.7
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
Mistral Large 2411
0.3
GPQA diamond
Qwen2.5-Max leads by +6.4
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
Mistral Large 2411
35.1
MATH level 5
Qwen2.5-Max leads by +16.9
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
Mistral Large 2411
50.3
OTIS Mock AIME 2024-2025
Qwen2.5-Max leads by +8.3
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Qwen2.5-Max
16.0
Mistral Large 2411
7.7
Full benchmark table
BenchmarkQwen2.5-MaxMistral Large 2411
Chatbot Arena Elo · Overall
1374.21304.7
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.
1.00.3
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
41.535.1
MATH level 5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
67.250.3
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
16.07.7
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
Alibaba Qwen logoQwen2.5-Max
Mistral AI logoMistral Large 2411$2.00$6.00131K tokens (~66 books)$30.00