Compare
Qwen 3 Max vs Gemini 2.5 Ultra
Qwen vs Google DeepMind. Specs, benchmarks, and real per-task cost — all in one page.
Verdict
Gemini 2.5 Ultra leads on LMSYS ELO (1385 vs 1295). Qwen 3 Max is ~3.7× cheaper on a 3:1 input:output blend. Qwen 3 Max is open-weights, the other is proprietary.
Qwen
Qwen 3 MaxAlibaba’s flagship. Strongest non-English coverage of any open model; dominant in Asian markets.
MultilingualOpen weightsCompetitive coding
Google DeepMind
Gemini 2.5 Ultra2M-token context, native video understanding, and Google’s deepest multimodal stack. The long-context king.
2M context windowNative videoBest multimodal reasoning
Pricing
Input / 1M$1.60$7.00
Output / 1M$6.40$21.00
Context128K2.0M
Max output16K64K
LicenseOpen weightsProprietary
Released2025-11-202026-02-05
Benchmarks
LMSYS ELO1295.01385.0
MMLU Pro84.090.4
HumanEval87.290.2
SWE-Bench—58.3
MATH85.192.0
MMMU71.882.1
IFEval85.589.7
Per-task cost
Summarize a 1-hour meeting transcript$0.027$0.115
Review a 500-line pull request$0.026$0.098
Answer a customer support ticket$0.0099$0.038
Extract structured data from a resume$0.014$0.056
Debug a stack trace with context$0.022$0.084
Per-call cost using published token counts for each task. Real-world prompts vary.