Decision support
Qwen3 Max vs Seed 1.6
Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.
Benchmark results
Head to head on 3 benchmarks both models report
- Qwen3 Max2leads
- Seed 1.61lead
Arena Text
Arena rating · Higher is better
- Qwen3 Max1423Arena #128CI 1417 to 1430
- Seed 1.6Not reported
Runs and sources
Qwen3 Max- default142395% CI 1417 to 1430 · 9,004 votes
Seed 1.6Not reported
FrontierMath-Tiers-1-3-v2-Private
Best published score · Higher is better
- Qwen3 Max18.9%#80 of 87
- Seed 1.6Not reported
Runs and sources
Qwen3 Max- default18.9%
Seed 1.6Not reported
Source:Epoch AI evaluationGPQA diamond
Best published score · Higher is better
- Qwen3 Max72.6%#102 of 161
- Seed 1.6Best77.6%+5.0 pts ahead · #92 of 161
Runs and sources
Qwen3 Max- default72.6%
Seed 1.6- default77.6%
Source:Epoch AI evaluationOTIS Mock AIME 2024-2025
Best published score · Higher is better
- Qwen3 MaxBest73.3%+3.9 pts ahead · #89 of 158
- Seed 1.669.4%#97 of 158
Runs and sources
Qwen3 Max- default73.3%
Seed 1.6- default69.4%
Source:Epoch AI evaluationSimpleQA Verified
Best published score · Higher is better
- Qwen3 MaxBest48.7%+31.3 pts ahead · #33 of 87
- Seed 1.617.4%#77 of 87
Runs and sources
Qwen3 Max- default48.7%
Seed 1.6- default17.4%
Source:Epoch AI evaluation
Each model's best published result is shown; "Not reported" means no matched evaluation, not a score of zero. Arena and DeepSWE ranks are the leaderboards' own; other ranks are among catalogue models with a score. Results from different harnesses or settings are not directly comparable.
Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.
Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.
Model specifications
API pricing · USD per 1M tokens
Capabilities and modalities
Architecture and availability
A dash means the field is not reported. Provider-specific performance and pricing may differ.