Grok 4.7 (high) vs MiniMax M3

Head-to-head on the Towards AI writing benchmark: same 10 real YouTube scripts, five runs each, scored blind by a three-family judge panel. Grok 4.7 (high) leads overall, 87.8 to 82.7.

Grok 4.7 (high)

#26 Elo 2186 · 87.8/100

MiniMax M3

#71 Elo 1672 · 82.7/100

Cost / script

$0.311 vs $0.023

Human baseline

90.9 Grok 4.7 (high) falls below it · MiniMax M3 falls below it

The verdict

Grok 4.7 (high) wins this one, and the board is not close: #26 at 2186.4 Elo and 87.79 overall, against #71, 1672.0 Elo and 82.70 overall for MiniMax M3. The 95% Elo intervals do not overlap (2130.8 to 2232.5 against 1632.1 to 1702.1). Where Grok 4.7 (high) pulls ahead: YouTube Best Practices (89.44 vs 79.79) and Slop Score (EQ-Bench + ours) (93.30 vs 85.83). MiniMax M3 still wins on Length Adherence (89.72 vs 74.12), so it is not a clean sweep. The trade is price: MiniMax M3 costs about $0.023 per article against $0.311 for Grok 4.7 (high), so you pay for the higher rank. MiniMax M3 publishes open weights; Grok 4.7 (high) does not. Default to Grok 4.7 (high). Reach for MiniMax M3 when length adherence, the lower price, and open weights matter more to you than the headline rank.

Pick Grok 4.7 (high) for the stronger board result, YouTube practices, and slop score.
Pick MiniMax M3 for length adherence, the lower price, and open weights.

Reading the Elo intervals. Each range estimates uncertainty around one model's Elo. We repeatedly sample from every model's recorded run scores on each task and recalculate the full ranking. Comparing these separate ranges does not test the Elo gap between two models. The tasks stay fixed, so the ranges do not measure how the ranking would change on new tasks.

Metric by metric

Blue bars: Grok 4.7 (high). Orange bars: MiniMax M3. Same 0–100 scale; the bold bar wins that metric.

Tone & Voice Match19% weight

89.8

82.2

Writing Craft & Clarity13% weight

87.9

83.9

Substance, Accuracy & Value15% weight

88.6

81.4

Continuity & Emotion14% weight

88.0

79.6

YouTube Best Practices12% weight

89.4

79.8

Hook Strength10% weight

88.1

84.8

Length Adherence8% weight

74.1

89.7

Slop Score (EQ-Bench + ours)5% weight

93.3

85.8

Visual Cue Quality4% weight

88.8

82.4

Everything else that differs

	Grok 4.7 (high)	MiniMax M3
Overall / 100	87.8	82.7
Writing Elo	2186	1672
Run-to-run spread (± overall std)	2.670	1.980
Cost per script (USD)	0.311	0.023
Avg latency (s)	519.0	109.9
Open weights	No	Yes

Full scorecards: Grok 4.7 (high) · MiniMax M3. How scoring works: methodology.

← All comparisons