Model Comparator

Compare up to four models using the same criteria.

Qwen3 8B (Non-reasoning)
Alibaba
Hermes 3 - Llama-3.1 70B
Nous Research

Differences only

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

Model Comparator
Metrics	Qwen3 8B (Non-reasoning) Alibaba	Hermes 3 - Llama-3.1 70B Nous Research
Intelligence	6	6
Math	24.3	—
Speed	Best: 41.7 t/s	31.5 t/s
TTFT	3.87 s	Best: 2.25 s
Input · $ / 1M tokens	Best: $0.20	$0.70×3.5 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $0.20	$0.70×3.5 relative to the lowest price among the compared models
Context window	Best: 131K	128K
Reasoning	No	No
Open weights	Yes	Yes

Intelligence

Qwen3 8B (Non-reasoning): 6
Hermes 3 - Llama-3.1 70B: 6

Math

Qwen3 8B (Non-reasoning): 24.3
Hermes 3 - Llama-3.1 70B: —

Speed

Qwen3 8B (Non-reasoning): Best: 41.7 t/s
Hermes 3 - Llama-3.1 70B: 31.5 t/s

TTFT

Qwen3 8B (Non-reasoning): 3.87 s
Hermes 3 - Llama-3.1 70B: Best: 2.25 s

Input · $ / 1M tokens

Qwen3 8B (Non-reasoning): Best: $0.20
Hermes 3 - Llama-3.1 70B: $0.70×3.5 relative to the lowest price among the compared models

Output · $ / 1M tokens

Qwen3 8B (Non-reasoning): Best: $0.20
Hermes 3 - Llama-3.1 70B: $0.70×3.5 relative to the lowest price among the compared models

Context window

Qwen3 8B (Non-reasoning): Best: 131K
Hermes 3 - Llama-3.1 70B: 128K

Reasoning

Qwen3 8B (Non-reasoning): No
Hermes 3 - Llama-3.1 70B: No

Open weights

Qwen3 8B (Non-reasoning): Yes
Hermes 3 - Llama-3.1 70B: 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 8B (Non-reasoning)6 · $0.20
Hermes 3 - Llama-3.1 70B6 · $0.70