Head-to-head AI model comparison graphic: MiniMax-M3 (MiniMax) vs MiniMax-M3.1-Flash (MiniMax). Intelligence index 18.9 vs 29.1; output speed 121 vs 147 tokens per second; time to first token 0.82s vs 1.0s; output price $1.20 vs $0.60 per million tokens; input price $0.30 vs $0.15 per million tokens. franklineh.com
MiniMax-M3 vs MiniMax-M3.1-Flash: head-to-head AI benchmark comparison. MiniMax-M3.1-Flash leads on intelligence index, output speed, output price and input price; MiniMax-M3 leads on time to first token.
Head to headBy Franklin AIUpdated

MiniMax-M3 vs MiniMax-M3.1-Flash: benchmarks, price and speed

MiniMax-M3.1-Flash leads the intelligence index 29.1 to 18.9. Compare price, speed, latency and a clear verdict.

Pick it for MiniMax-M3

  • Shorter wait for the first token: 0.82 seconds against 1.0 seconds.

Pick it for MiniMax-M3.1-Flash

  • Higher intelligence index: 29.1 against 18.9.
  • Lower cost: $0.27 against $0.54 for 1 million input and 200,000 output tokens.
  • Faster output once writing: 147 tokens per second against 121 tokens per second, which wins on total time beyond about 150 tokens.

By the numbers

MetricMiniMax-M3MiniMax-M3.1-Flash
Intelligence Index18.929.1
Input price (per 1M tokens)$0.30$0.15
Output price (per 1M tokens)$1.20$0.60
Output speed (tokens/s)121147
Time to first token0.82s1.0s
Release date2026-06-012026-10-19

MiniMax-M3 and MiniMax-M3.1-Flash share a maker, MiniMax, but not a price sheet or a benchmark profile. The headline gap is on the intelligence index, where MiniMax-M3.1-Flash scores 29.1 and MiniMax-M3 18.9. All numbers are the catalogue's recorded values; nobody ran either model by hand for this page.

MiniMax-M3.1-Flash leads on the intelligence index

MiniMax-M3 records 18.9 on the intelligence index and MiniMax-M3.1-Flash records 29.1. This is a substantial lead, not a near miss.

For context, that places MiniMax-M3 79th and MiniMax-M3.1-Flash 59th out of 109 scored models still on offer.

For coding or maths work specifically, the catalogue has no dedicated index on either side yet.

Generation gap

The release dates are June 1, 2026 for MiniMax-M3 and October 19, 2026 for MiniMax-M3.1-Flash, about 5 months apart.

How fast they respond

MiniMax-M3 generates about 121 tokens per second and MiniMax-M3.1-Flash about 147 tokens per second. MiniMax-M3.1-Flash is ahead by 22% on throughput. Before any text appears, MiniMax-M3 takes 0.82 seconds and MiniMax-M3.1-Flash 1.0 seconds. So the two pull in opposite directions, with MiniMax-M3 quicker off the mark and MiniMax-M3.1-Flash quicker once it gets going; the crossover is around 150 tokens.

Add the two numbers up for a 400-token reply and MiniMax-M3.1-Flash finishes first: 4.1 seconds for MiniMax-M3, 3.7 seconds for MiniMax-M3.1-Flash.

Price per token

Per million tokens, MiniMax-M3 charges $0.30 for input and $1.20 for output, while MiniMax-M3.1-Flash charges $0.15 and $0.60. For output tokens, MiniMax-M3 is twice the price of MiniMax-M3.1-Flash.

A reference job of 1 million input tokens and 200,000 output tokens costs $0.54 with MiniMax-M3 and $0.27 with MiniMax-M3.1-Flash, so MiniMax-M3.1-Flash saves $0.27. Scale it up to a month of coding-assistant traffic at 30 million input and 3 million output tokens and the bill is $12.60 for MiniMax-M3 against $6.30 for MiniMax-M3.1-Flash. Blended at three input tokens per output token, the effective rates are $0.525 for MiniMax-M3 and $0.262 for MiniMax-M3.1-Flash.

Is the price in proportion?

Per point of intelligence index, MiniMax-M3 costs $0.028 of blended price per million tokens and MiniMax-M3.1-Flash $0.0090. MiniMax-M3.1-Flash scores higher and costs less per point, so on price per point there is nothing to trade off.

Frequently asked questions

Is MiniMax-M3 better than MiniMax-M3.1-Flash?

It depends on what you need: MiniMax-M3.1-Flash scores higher on the intelligence index, 29.1 to 18.9; MiniMax-M3.1-Flash is 50% cheaper on blended price; MiniMax-M3.1-Flash streams output 1.2 times as fast; and MiniMax-M3 reaches its first token sooner.

Which is newer, MiniMax-M3 or MiniMax-M3.1-Flash?

MiniMax-M3.1-Flash is newer. It was released on October 19, 2026, about 5 months after MiniMax-M3 (June 1, 2026).

Which is faster, MiniMax-M3 or MiniMax-M3.1-Flash?

MiniMax-M3.1-Flash generates output faster, at 147 tokens per second against 121 tokens per second. MiniMax-M3 reaches its first token sooner (0.82 seconds against 1.0 seconds). Counting the first-token wait, MiniMax-M3 finishes short replies first and MiniMax-M3.1-Flash pulls ahead beyond about 150 tokens.

Where do these numbers come from?

The figures are the recorded benchmark, price and speed data in Franklin AI's model catalogue. This page is written from that data automatically; neither model was tested by hand for it.

Are MiniMax-M3 and MiniMax-M3.1-Flash from the same company?

Both are MiniMax models, listed as separate models in the catalogue. MiniMax-M3 was released on June 1, 2026 and MiniMax-M3.1-Flash on October 19, 2026.

Final whistle

Bottom line: MiniMax-M3.1-Flash has more going for it here, but MiniMax-M3 is not without an argument. Pick MiniMax-M3.1-Flash if you need the higher overall score (29.1 against 18.9) and cost matters ($0.60 against $1.20 per million output tokens). Pick MiniMax-M3 if users are waiting on the first word.

Where the numbers come from

The scores, speed and prices in this comparison come from independent third-party model evaluations that Franklin AI syncs each day, and the article was written from a snapshot of them. For the latest results, open the MiniMax-M3 and MiniMax-M3.1-Flash pages. The AI Benchmark methodology explains how that data is collected and shown.

Comments (0)

No comments yet

Be the first to share your thoughts!