MiniMax M3
Not tested yet
Language modelActive
MiniMax M3
MiniMax
- Released
- June 2026
- Data date
- September 8, 2026
- Intelligence
- Overall score
- Speed
- 105.3 tokens/sOutput throughput
- Price
- Input · Output / 1M tokens
No published category-wide ranking is available for this model.
Entries 1-10 of 10. Page 1 of 1.
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
Artificial Analysis Intelligence Index (Show measurement, test conditions, and source)
- Source value
- 29.6125932236316
- Score
- 29.6125932236316
- Metric
- points
- Unit
- points
- Direction
- Higher is better
- Comparison cohort
- research:minimax-m3:0
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. unknown
AA-Briefcase Elo (Show measurement, test conditions, and source)
- Source value
- 1096.03
- Score
- 1096.03
- Metric
- elo
- Unit
- elo
- Direction
- Higher is better
- Comparison cohort
- research:minimax-m3:1
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. unknown
AA-Omniscience Index (Show measurement, test conditions, and source)
- Source value
- 1.35
- Score
- 1.35
- Metric
- points
- Unit
- points
- Direction
- Higher is better
- Comparison cohort
- research:minimax-m3:2
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. unknown
Output speed (Show measurement, test conditions, and source)
- Source value
- 105.28988807545
- Score
- 105.28988807545
- Metric
- tokens/s
- Unit
- tokens/s
- Direction
- Higher is better
- Comparison cohort
- research:minimax-m3:3
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. unknown
- Context
- Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API.
Time per Intelligence Index Task (Show measurement, test conditions, and source)
- Source value
- 7.3753045028032975
- Score
- 7.3753045028032975
- Metric
- minutes
- Unit
- minutes
- Direction
- Lower is better
- Comparison cohort
- research:minimax-m3:4
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. unknown
- Context
- Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API.
Latency reasoning time (Show measurement, test conditions, and source)
- Source value
- 18.995176427263495
- Score
- 18.995176427263495
- Metric
- seconds
- Unit
- seconds
- Direction
- Lower is better
- Comparison cohort
- research:minimax-m3:5
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. unknown
- Context
- Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API.
Latency input time (Show measurement, test conditions, and source)
- Source value
- 1.3112509545
- Score
- 1.3112509545
- Metric
- seconds
- Unit
- seconds
- Direction
- Lower is better
- Comparison cohort
- research:minimax-m3:6
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. unknown
- Context
- Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API.
Answer generation time (end-to-end timing breakdown) (Show measurement, test conditions, and source)
- Source value
- 4.7487941068158745
- Score
- 4.7487941068158745
- Metric
- seconds
- Unit
- seconds
- Direction
- Lower is better
- Comparison cohort
- research:minimax-m3:7
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. unknown
- Context
- Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API.
End-to-end reasoning time component (Show measurement, test conditions, and source)
- Source value
- 18.995176427263495
- Score
- 18.995176427263495
- Metric
- seconds
- Unit
- seconds
- Direction
- Lower is better
- Comparison cohort
- research:minimax-m3:8
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. unknown
- Context
- Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API.
End-to-end input time component (Show measurement, test conditions, and source)
- Source value
- 1.3112509545
- Score
- 1.3112509545
- Metric
- seconds
- Unit
- seconds
- Direction
- Lower is better
- Comparison cohort
- research:minimax-m3:9
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. unknown
- Context
- Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API.
Our model tests
Community tests you can inspect
Compare how the models respond to the same prompt. Each test shows the first attempt, with no subsequent fixes to the generated code. These results do not contribute to an overall score.
Pelican on a bicycle
A community classic for free-form SVG drawing.
Prompt and test conditions
Generate an SVG of a pelican riding a bicycle
Token limit including reasoning: 8,192 tokens
Task origin (Simon Willison)Pricing
Published prices
Prices apply to the stated unit. Resolution, output length, and provider can change the cost.
Cost example
100 API requests
$0.09
100 requests with 1,000 input and 500 output tokens each calculate to $0.09. Input accounts for $0.03; output accounts for $0.06.
- Input price
- $0.3 / 1M tokensBase tier for each request
- Output price
- $1.2 / 1M tokensBase tier for each request
The calculation uses documented token prices and no cache discount. It excludes extra tools, tax, reasoning tokens, and further hidden output tokens.
Open sourceHead-to-head comparisons
Compare this model
Each matchup compares this model with exactly one other model from the same category.
There are no published direct comparisons for this model yet.
More models
Models from the same selection
All AI models
Evidence
Sources and data date
Every statement links to its underlying documentation or leaderboard.
- Speed
MiniMax. Output speed after the first streaming chunk, not total response time. Retrieved September 8, 2026.
- Price
Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs.
Research date September 8, 2026. 2 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Open evidence questions and research notes (original wording)
Not found in the inspected sources
parameters-billions. No exact variant-specific value was located; the available page describes a related/base model.
Not found in the inspected sources
release-date. The checked official pricing page names MiniMax M3 but does not publish a release date.
Not found in the inspected sources
active-parameters-billions. No exact variant-specific value was located; the available page describes a related/base model.
Not found in the inspected sources
knowledge-cutoff. No exact variant-specific value was located; the available page describes a related/base model.
Not found in the inspected sources
profile-benchmarks. Checked the exact primary model card/API or release page; no usable labeled benchmark score was published/found for this model.
Unresolved
model-card. Official pricing page was readable, but an exact M3 model card/technical specification page was not located.
Unresolved
source-discrepancy. The checked official pricing page exposes pricing but no exact model card or benchmark table.