modelgrep

OpenAI: o3 Mini High vs Qwen: Qwen3 235B A22B Instruct 2507

Qwen: Qwen3 235B A22B Instruct 2507 wins on more metrics (7 of 9), but the right pick depends on what you optimize for — see the breakdown below.

MetricOpenAI: o3 Mini HighQwen: Qwen3 235B A22B Instruct 2507
Intelligence Index25.225.0
Coding Index17.322.1
GPQA Diamond77%75%
Design Arena Elo1103
Speed (tokens/sec)1183
Latency328ms287ms
Input price /M$1.10$0.090
Output price /M$4.40$0.100
Context window200K262K
CapabilitiesReasoningToolsJSONToolsJSON