modelgrep

Mistral: Mistral Large 3 2512 vs Qwen: Qwen3 30B A3B Thinking 2507

MMistral: Mistral Large 3 2512mistralai/mistral-large-2512VSQQwen: Qwen3 30B A3B Thinking 2507qwen/qwen3-30b-a3b-thinking-2507

Qwen: Qwen3 30B A3B Thinking 2507 wins on more metrics (5 of 9), but the right pick depends on what you optimize for — see the breakdown below.

MetricMistral: Mistral Large 3 2512Qwen: Qwen3 30B A3B Thinking 2507
Intelligence Index22.8✓22.4
Coding Index22.7✓14.6
GPQA Diamond68%71%✓
Design Arena Elo1206✓975
Speed (tokens/sec)3098✓
Latency787ms560ms✓
Input price /M$0.500$0.080✓
Output price /M$1.50$0.400✓
Context window262K✓131K
CapabilitiesToolsJSONVisionReasoningToolsJSON
Mistral: Mistral Large 3 2512 details →Qwen: Qwen3 30B A3B Thinking 2507 details →