Decision support
Qwen3 VL 235B A22B Thinking vs Magistral Small 1.2
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 VL 235B A22B Thinking1395Arena #173CI 1388 to 1402
- Magistral Small 1.2Not reported
Runs and sources
Qwen3 VL 235B A22B Thinking- default139595% CI 1388 to 1402 · 7,835 votes
Magistral Small 1.2Not reported
Arena Vision
Arena rating · Higher is better
- Qwen3 VL 235B A22B Thinking1188Arena #102CI 1175 to 1200
- Magistral Small 1.2Not reported
Runs and sources
Qwen3 VL 235B A22B Thinking- default118895% CI 1175 to 1200 · 2,379 votes
Magistral Small 1.2Not reported
GPQA diamond
Best published score · Higher is better
- Qwen3 VL 235B A22B ThinkingNot reported
- Magistral Small 1.247.6%#142 of 161
Runs and sources
Qwen3 VL 235B A22B ThinkingNot reported
Magistral Small 1.2- default47.6%
Source:Epoch AI evaluationOTIS Mock AIME 2024-2025
Best published score · Higher is better
- Qwen3 VL 235B A22B ThinkingNot reported
- Magistral Small 1.228.1%#130 of 158
Runs and sources
Qwen3 VL 235B A22B ThinkingNot reported
Magistral Small 1.2- default28.1%
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.