modelgrep

OpenAI: GPT-4o (2024-11-20) vs Qwen: Qwen3 VL 8B Thinking

OOpenAI: GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20VSQQwen: Qwen3 VL 8B Thinkingqwen/qwen3-vl-8b-thinking

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

MetricOpenAI: GPT-4o (2024-11-20)Qwen: Qwen3 VL 8B Thinking
Intelligence Index17.3✓16.7
Coding Index16.7✓9.8
GPQA Diamond54%58%✓
Design Arena Elo——
Speed (tokens/sec)62129✓
Latency452ms✓502ms
Input price /M$2.50$0.117✓
Output price /M$10.00$1.36✓
Context window128K256K✓
CapabilitiesToolsJSONVisionReasoningToolsJSONVision
OpenAI: GPT-4o (2024-11-20) details →Qwen: Qwen3 VL 8B Thinking details →