INTELLIGENCE
40.6
Media Cap quality axis
MiniMax · ProprietaryMiniMax: MiniMax M3
Active
Model portfolio
MiniMax: MiniMax M3
Tap a star to rate
MiniMax · Released 2026-05-31 · v2026-05-31 · Closed · Context 1.0M tokens
Language Cap
73
Cadle Language Cap 73 · 86%
Benchmark average
82.0
Not enough benchmark results yet
Pricing
$0.30
$1.20 / 1M out · 51.9 pts/$
CADLE CAP vs MODEL MATRIX
Cadle Cap ranks models on every published score we have for them — harder benchmarks weigh more. Missing tests are skipped, not zeroed. It answers who is stronger than whom in today's pool.
Model Matrix is the datasheet: Overall, Intelligence, Coding, Agentic, MMLU, GPQA, Math, LiveCodeBench, HumanEval, Reason, ARC-AGI. A dash means unmeasured. AVG is an importance-weighted mean of that model's filled cells only.
MODEL MATRIX · TRUTH CENTER CELLS
Overall
61.2
Intelligence
29.2
Coding
69.0
Agentic
88.9
MMLU
84.6
GPQA
92.9
Math
85.7
LiveCodeBench
64.7
HumanEval
No data yet
Reason
93.8
ARC-AGI
No data yet
Coverage AVG
82.0
Cadle Cap ranks models with within-benchmark percentiles so ARC-AGI ~40 and MMLU ~90 never compete raw. Coverage AVG is an importance-weighted mean of filled expert cells only — blanks are skipped, not zeroed.
ANALYSIS · TRUTH CENTER
Hard benches (GPQA · ARC-AGI · LCB · Agentic) sit left — a mid-40 on ARC-AGI can still be frontier. Broader benches on the right are easier and often higher.
CADLE INSIGHTS
Only measured signals
CODING
69.0
Media Cap quality axis
AGENTIC
88.9
Media Cap quality axis
MATH
85.7
Media Cap quality axis
MATRIX OVERALL
61.2
AVG 82.0 across matrix cells
STRONGEST SIGNAL
Intelligence
Cap axis 40.6
BLENDED $/1M
$1.50
In $0.30 · Out $1.20
VALUE INDEX
40.8
Quality ÷ blended $/1M (higher is better)
SPEED · COST · QUALITY
Measured matrix / AA / gateway rows only.
- Overall (Matrix)
- 61.2
- Cap Intelligence
- 77.9
- AA / Intel index
- 29.2
- Cap Coding
- 62.1
- Matrix Coding
- 69.0
- Input $/1M
- $0.30
- Output $/1M
- $1.20
- Value pts/$
- 51.94
DESCRIPTION + DETAILS
PROVIDER
MiniMax
RELEASE
2026-05-31
CONTEXT
1.0M tokens
STATUS
ACTIVE
COMMUNITY REVIEWS
OPERATOR NOTES
Quality, latency, cost, and failure modes — not marketing copy.
No reviews yet
WRITE A REVIEW
Tap a star to rate
Stored on this device · synced when signed in
No operator notes yet
First review sets the tone for how teams evaluate MiniMax: MiniMax M3.
MODEL COMPARISON
| Metric | |
|---|---|
| Provider | MiniMax |
| Release | 2026-05-31 |
| Input / 1M | $0.30 |
| Output / 1M | $1.20 |
| Context | 1.0M tokens |
| Cadle Cap | 73 |
| Cap board | Cadle Language Cap 73 |
DATA PROVENANCE
Scores may use different scales — check the Benchmarks tab for source links.
- Supabase models
- Cadle public observations
SOURCE TRACKING
Evidence linked to this model — listing, hub, benchmarks, or live gateway prices.
API
MiniMax listing
MEASURED CELLS
Same Truth Center numbers as the datasheet above. Accuracy, reliability, safety, and cost scores are not invented.
Overall61.2
AA IQ29.2
Coding69
Agentic88.9
MMLU84.6
GPQA92.9
Math85.7
LiveCodeBench64.7