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

Qwen3.7 Max
29.5
MiMo-V2.6-Pro
Best: 29.9

Coding

Qwen3.7 Max
66
MiMo-V2.6-Pro
—

Agentic

Qwen3.7 Max
22.5
MiMo-V2.6-Pro
—

Cyber Index

Qwen3.7 Max
—
MiMo-V2.6-Pro
56.1%

Speed

Qwen3.7 Max
Best: 202 t/s
MiMo-V2.6-Pro
40 t/s

TTFT

Qwen3.7 Max
Best: 2.19 s
MiMo-V2.6-Pro
3.36 s

Input · $ / 1M tokens

Qwen3.7 Max
$2.50×5.7 relative to the lowest price among the compared models
MiMo-V2.6-Pro
Best: $0.435

Output · $ / 1M tokens

Qwen3.7 Max
$7.50×8.6 relative to the lowest price among the compared models
MiMo-V2.6-Pro
Best: $0.87

Context window

Qwen3.7 Max
1M
MiMo-V2.6-Pro
1M

Reasoning

Qwen3.7 Max
Yes
MiMo-V2.6-Pro
Yes

Open weights

Qwen3.7 Max
No
MiMo-V2.6-Pro
Yes

Cost / task

Qwen3.7 Max
$0.932×3.6 relative to the lowest price among the compared models
MiMo-V2.6-Pro
Best: $0.257

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
  • Qwen3.7 Max29.5 · $0.932
  • MiMo-V2.6-Pro29.9 · $0.257

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