MiniMax-M3.1-Flash vs Claude Sonnet 5.5 (Max, Default Fallback)

Claude Sonnet 5.5 (Max, Default Fallback) scores 54.5 on the Artificial Analysis Intelligence Index, against 29.1 for MiniMax-M3.1-Flash. MiniMax-M3.1-Flash costs $0.262 per million tokens (3:1 blend), against $4 for Claude Sonnet 5.5 (Max, Default Fallback). Claude Sonnet 5.5 (Max, Default Fallback) generates 151 t/s, against 135 t/s for MiniMax-M3.1-Flash. Both accept a context of 1M tokens.

Comparison generated from the catalogue data. Add or remove models below to refine it.

2 models compared

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

Intelligence

MiniMax-M3.1-Flash
29.1
Claude Sonnet 5.5 (Max, Default Fallback)
Best: 54.5

Speed

MiniMax-M3.1-Flash
135 t/s
Claude Sonnet 5.5 (Max, Default Fallback)
Best: 151 t/s

TTFT

MiniMax-M3.1-Flash
Best: 1.48 s
Claude Sonnet 5.5 (Max, Default Fallback)
250 s

Input · $ / 1M tokens

MiniMax-M3.1-Flash
Best: $0.15
Claude Sonnet 5.5 (Max, Default Fallback)
$2×13.3 relative to the lowest price among the compared models

Output · $ / 1M tokens

MiniMax-M3.1-Flash
Best: $0.60
Claude Sonnet 5.5 (Max, Default Fallback)
$10×16.7 relative to the lowest price among the compared models

Context window

MiniMax-M3.1-Flash
1M
Claude Sonnet 5.5 (Max, Default Fallback)
1M

Reasoning

MiniMax-M3.1-Flash
Yes
Claude Sonnet 5.5 (Max, Default Fallback)
Yes

Open weights

MiniMax-M3.1-Flash
Yes
Claude Sonnet 5.5 (Max, Default Fallback)
No

Cost / task

MiniMax-M3.1-Flash
Best: $0.491
Claude Sonnet 5.5 (Max, Default Fallback)
$10.02×20.4 relative to the lowest price among the compared models

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
  • MiniMax-M3.1-Flash29.1 · $0.491
  • Claude Sonnet 5.5 (Max, Default Fallback)54.5 · $10.02

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