Decision support
Qwen3 Max vs x-AI/Grok-Code-Fast 1
Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.
Benchmark results
Arena Text
Arena rating · Higher is better
- Qwen3 Max1423Arena #128CI 1417 to 1430
- x-AI/Grok-Code-Fast 1Not reported
Runs and sources
Qwen3 Max- default142395% CI 1417 to 1430 · 9,004 votes
x-AI/Grok-Code-Fast 1Not reported
Arena WebDev
Arena rating · Higher is better
- Qwen3 MaxNot reported
- x-AI/Grok-Code-Fast 11164Arena #154CI 1135 to 1193
Runs and sources
Qwen3 MaxNot reported
x-AI/Grok-Code-Fast 1- default116495% CI 1135 to 1193 · 770 votes
FrontierMath-Tiers-1-3-v2-Private
Best published score · Higher is better
- Qwen3 Max18.9%#80 of 87
- x-AI/Grok-Code-Fast 1Not reported
Runs and sources
Qwen3 Max- default18.9%
x-AI/Grok-Code-Fast 1Not reported
Source:Epoch AI evaluationGPQA diamond
Best published score · Higher is better
- Qwen3 Max72.6%#102 of 161
- x-AI/Grok-Code-Fast 1Not reported
Runs and sources
Qwen3 Max- default72.6%
x-AI/Grok-Code-Fast 1Not reported
Source:Epoch AI evaluationOTIS Mock AIME 2024-2025
Best published score · Higher is better
- Qwen3 Max73.3%#89 of 158
- x-AI/Grok-Code-Fast 1Not reported
Runs and sources
Qwen3 Max- default73.3%
x-AI/Grok-Code-Fast 1Not reported
Source:Epoch AI evaluationSimpleQA Verified
Best published score · Higher is better
- Qwen3 Max48.7%#33 of 87
- x-AI/Grok-Code-Fast 1Not reported
Runs and sources
Qwen3 Max- default48.7%
x-AI/Grok-Code-Fast 1Not reported
Source:Epoch AI evaluationTerminal Bench
Best published score · Higher is better
- Qwen3 MaxNot reported
- x-AI/Grok-Code-Fast 125.8%#42 of 49
Runs and sources
Qwen3 MaxNot reported
x-AI/Grok-Code-Fast 1- default25.8%Mini-SWE-Agent
- default25.8%Mini-SWE-Agent
- default14.2%Terminus 2
- default14.2%Terminus 2
Sources:Terminal-Bench v2 LeaderboardOriginal-source terms applyhttps://www.tbench.ai/leaderboard/terminal-bench/2.0Original-source terms apply
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.
Original-source terms apply to evaluations credited to their original publishers.
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.