Model Comparator

Compare up to four models using the same criteria.

2 models compared

  1. Kimi K2 Thinking

    Moonshot AI

  2. MiMo-V2.5

    Xiaomi

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

Intelligence

Kimi K2 Thinking
Best: 22
MiMo-V2.5
21.8

Coding

Kimi K2 Thinking
21
MiMo-V2.5
Best: 56.8

Math

Kimi K2 Thinking
94.7
MiMo-V2.5
—

Agentic

Kimi K2 Thinking
—
MiMo-V2.5
15.8

Speed

Kimi K2 Thinking
Best: 116 t/s
MiMo-V2.5
54.4 t/s

TTFT

Kimi K2 Thinking
1.69 s
MiMo-V2.5
Best: 1.63 s

Input · $ / 1M tokens

Kimi K2 Thinking
$0.60×4.5 relative to the lowest price among the compared models
MiMo-V2.5
Best: $0.133

Output · $ / 1M tokens

Kimi K2 Thinking
$2.50×9.4 relative to the lowest price among the compared models
MiMo-V2.5
Best: $0.266

Context window

Kimi K2 Thinking
1M
MiMo-V2.5
1M

Reasoning

Kimi K2 Thinking
Yes
MiMo-V2.5
Yes

Open weights

Kimi K2 Thinking
Yes
MiMo-V2.5
Yes

Cost / task

Kimi K2 Thinking
—
MiMo-V2.5
$0.0418

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 ↗Price / 1M tokens
  • Kimi K2 Thinking22 · $1.08
  • MiMo-V2.521.8 · $0.166

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