Model Comparator

Compare up to four models using the same criteria.

Gemma 4 26B A4B (Reasoning)
Google
Claude 4.5 Haiku (Non-reasoning)
Anthropic

Differences only

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

Model Comparator
Metrics	Gemma 4 26B A4B (Reasoning) Google	Claude 4.5 Haiku (Non-reasoning) Anthropic
Intelligence	16.7	Best: 16.9
Coding	39.3	Best: 43.9
Math	—	39
Agentic	2.9	Best: 8
Speed	Best: 95.3 t/s	81.9 t/s
TTFT	0.94 s	Best: 0.58 s
Input · $ / 1M tokens	Best: $0.10	$1×10 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $0.34	$5×14.7 relative to the lowest price among the compared models
Context window	1M	1M
Reasoning	Yes	No
Open weights	Yes	No

Intelligence

Gemma 4 26B A4B (Reasoning): 16.7
Claude 4.5 Haiku (Non-reasoning): Best: 16.9

Coding

Gemma 4 26B A4B (Reasoning): 39.3
Claude 4.5 Haiku (Non-reasoning): Best: 43.9

Math

Gemma 4 26B A4B (Reasoning): —
Claude 4.5 Haiku (Non-reasoning): 39

Agentic

Gemma 4 26B A4B (Reasoning): 2.9
Claude 4.5 Haiku (Non-reasoning): Best: 8

Speed

Gemma 4 26B A4B (Reasoning): Best: 95.3 t/s
Claude 4.5 Haiku (Non-reasoning): 81.9 t/s

TTFT

Gemma 4 26B A4B (Reasoning): 0.94 s
Claude 4.5 Haiku (Non-reasoning): Best: 0.58 s

Input · $ / 1M tokens

Gemma 4 26B A4B (Reasoning): Best: $0.10
Claude 4.5 Haiku (Non-reasoning): $1×10 relative to the lowest price among the compared models

Output · $ / 1M tokens

Gemma 4 26B A4B (Reasoning): Best: $0.34
Claude 4.5 Haiku (Non-reasoning): $5×14.7 relative to the lowest price among the compared models

Context window

Gemma 4 26B A4B (Reasoning): 1M
Claude 4.5 Haiku (Non-reasoning): 1M

Reasoning

Gemma 4 26B A4B (Reasoning): Yes
Claude 4.5 Haiku (Non-reasoning): No

Open weights

Gemma 4 26B A4B (Reasoning): Yes
Claude 4.5 Haiku (Non-reasoning): No

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.

Gemma 4 26B A4B (Reasoning)16.7 · $0.16
Claude 4.5 Haiku (Non-reasoning)16.9 · $2