Model Comparator

Compare up to four models using the same criteria.

2 models compared

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

Intelligence

Agnes 2.5 Pro Theta
24
DeepSeek V4 Flash 0420 (Max)
Best: 24.2

Coding

Agnes 2.5 Pro Theta
—
DeepSeek V4 Flash 0420 (Max)
56.2

Agentic

Agnes 2.5 Pro Theta
—
DeepSeek V4 Flash 0420 (Max)
22.2

Speed

Agnes 2.5 Pro Theta
Best: 198 t/s
DeepSeek V4 Flash 0420 (Max)
58.3 t/s

TTFT

Agnes 2.5 Pro Theta
2.44 s
DeepSeek V4 Flash 0420 (Max)
Best: 1.78 s

Input · $ / 1M tokens

Agnes 2.5 Pro Theta
Best: $0.10
DeepSeek V4 Flash 0420 (Max)
$0.112×1.1 relative to the lowest price among the compared models

Output · $ / 1M tokens

Agnes 2.5 Pro Theta
$0.30×1.3 relative to the lowest price among the compared models
DeepSeek V4 Flash 0420 (Max)
Best: $0.234

Context window

Agnes 2.5 Pro Theta
1M
DeepSeek V4 Flash 0420 (Max)
1M

Reasoning

Agnes 2.5 Pro Theta
Yes
DeepSeek V4 Flash 0420 (Max)
Yes

Open weights

Agnes 2.5 Pro Theta
No
DeepSeek V4 Flash 0420 (Max)
Yes

Cost / task

Agnes 2.5 Pro Theta
$0.575×5.8 relative to the lowest price among the compared models
DeepSeek V4 Flash 0420 (Max)
Best: $0.0983

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.

Intelligence Indexmost efficient ↗Cost per task
  • Agnes 2.5 Pro Theta24 · $0.575
  • DeepSeek V4 Flash 0420 (Max)24.2 · $0.0983

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy