modelgrep

Mistral: Mistral Medium 3.1 vs Qwen: Qwen3 30B A3B Thinking 2507

Qwen: Qwen3 30B A3B Thinking 2507 wins on more metrics (5 of 8), but the right pick depends on what you optimize for — see the breakdown below.

MetricMistral: Mistral Medium 3.1Qwen: Qwen3 30B A3B Thinking 2507
Intelligence Index21.322.4
Coding Index18.314.6
GPQA Diamond59%71%
Design Arena Elo1192975
Speed (tokens/sec)8126
Latency289ms473ms
Input price /M$0.400$0.080
Output price /M$2.00$0.400
Context window131K131K
CapabilitiesToolsJSONVisionReasoningToolsJSON