Compare

Four models, one page

Pick the models you are actually choosing between. Every row is scaled within itself, so a bar means something next to its neighbours and nothing across rows.

Slot 1

Slot 2

Slot 3

Slot 4

Specification	MiniMax M1MiniMax	Claude Opus 5Anthropic
Released	Jun 17, 2025	Jul 24, 2026
Context window	1M	1M
Max output	40K	128K
Input / 1M	$0.55	$5
Output / 1M	$2.2	$25
Cost per task	$0.20	$2.25
Arena Elo	—	1,393
Serving providers	2	5
Parameters	Undisclosed	Undisclosed
Licence	Proprietary	Proprietary
Capabilities	Reasoning Tool use	Reasoning Tool use Vision

Metrics side by side

Each row is scaled to the largest value in that row — bars compare within a row, never across rows

MiniMax M1
Claude Opus 5

Intelligence Index
MiniMax M1not measured
Claude Opus 5
63.1
Coding Index
MiniMax M1not measured
Claude Opus 5
78.0
Agentic Index
MiniMax M1not measured
Claude Opus 5
59.2
Output speed
MiniMax M1
76 t/s
Claude Opus 5
87 t/s
Context window
MiniMax M1
1M
Claude Opus 5
1M
Latency · lower is better
MiniMax M1
769ms
Claude Opus 5
1.12s
Blended price / 1M · lower is better
MiniMax M1
$0.963
Claude Opus 5
$10
Cost per task · lower is better
MiniMax M1
$0.20
Claude Opus 5
$2.25

Rows marked “lower is better” still draw a longer bar for a larger number — read the value, not just the length. Arena Elo is in the specification table above instead: it has no meaningful zero, so a bar would flatten the gaps.

View as table

Metric	MiniMax M1	Claude Opus 5
Intelligence Index	—	63.1
Coding Index	—	78.0
Agentic Index	—	59.2
Output speed	76 t/s	87 t/s
Context window	1M	1M
Latency · lower is better	769ms	1.12s
Blended price / 1M · lower is better	$0.963	$10
Cost per task · lower is better	$0.20	$2.25

Evaluation scores

Percentage correct on a common 0–100% scale

MiniMax M1
Claude Opus 5

GPQA Diamond
MiniMax M1not measured
Claude Opus 5
93.2%
Humanity's Last Exam
MiniMax M1not measured
Claude Opus 5
54.9%
SciCode
MiniMax M1not measured
Claude Opus 5
55.7%
τ²-bench
MiniMax M1not measured
Claude Opus 5
42.1%
AA-LCR long context
MiniMax M1not measured
Claude Opus 5
75.7%

A missing bar means that evaluation was not run for that model — it is not a zero.

View as table

Evaluation	MiniMax M1	Claude Opus 5
GPQA Diamond	—	93.2%
Humanity's Last Exam	—	54.9%
SciCode	—	55.7%
τ²-bench	—	42.1%
Terminal-Bench Hard	—	—
LiveCodeBench	—	—
AA-LCR long context	—	75.7%
AIME 2025	—	—

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).