Model Comparator

Compare up to four models using the same criteria.

Gemini 2.0 Flash Thinking Experimental (Dec '24)
Google
Qwen3 30B A3B (Non-reasoning)
Alibaba

Differences only

✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.

Model Comparator
Metrics	Gemini 2.0 Flash Thinking Experimental (Dec '24) Google	Qwen3 30B A3B (Non-reasoning) Alibaba
Intelligence	6.6	6.6
Math	—	21.7
Speed	—	98.7 t/s
TTFT	—	0.59 s
Input · $ / 1M tokens	—	$0.12
Output · $ / 1M tokens	—	$0.50
Context window	Best: 2M	33K
Reasoning	Yes	No
Open weights	No	Yes

Intelligence

Gemini 2.0 Flash Thinking Experimental (Dec '24): 6.6
Qwen3 30B A3B (Non-reasoning): 6.6

Math

Gemini 2.0 Flash Thinking Experimental (Dec '24): —
Qwen3 30B A3B (Non-reasoning): 21.7

Speed

Gemini 2.0 Flash Thinking Experimental (Dec '24): —
Qwen3 30B A3B (Non-reasoning): 98.7 t/s

TTFT

Gemini 2.0 Flash Thinking Experimental (Dec '24): —
Qwen3 30B A3B (Non-reasoning): 0.59 s

Input · $ / 1M tokens

Gemini 2.0 Flash Thinking Experimental (Dec '24): —
Qwen3 30B A3B (Non-reasoning): $0.12

Output · $ / 1M tokens

Gemini 2.0 Flash Thinking Experimental (Dec '24): —
Qwen3 30B A3B (Non-reasoning): $0.50

Context window

Gemini 2.0 Flash Thinking Experimental (Dec '24): Best: 2M
Qwen3 30B A3B (Non-reasoning): 33K

Reasoning

Gemini 2.0 Flash Thinking Experimental (Dec '24): Yes
Qwen3 30B A3B (Non-reasoning): No

Open weights

Gemini 2.0 Flash Thinking Experimental (Dec '24): No
Qwen3 30B A3B (Non-reasoning): Yes

Each reasoning level remains a separate configuration.

Score and cost

Each line joins the reasoning levels of a compared model; the large point marks the configuration in the table. The top-right corner holds the best score for the lowest cost. Select another point to compare that level.

Qwen3 30B A3B (Non-reasoning)6.6 · $0.215

Not plotted for lack of data on these axes: Gemini 2.0 Flash Thinking Experimental (Dec '24).