MiniMax M3
Language modelActive
MiniMax M3
MiniMax
- Released
- June 1, 2026
- Data date
- September 8, 2026
- Predecessor
- MiniMax M2.7
- Benchmark-Meta-Score
- Standard error ± 3.8
- Speed
- 105.3 tokens/sOutput throughput
- Price
- Input · Output / 1M tokens
MiniMax M3 combines a 1M-token context with native image and video input plus computer use. Its distinctive feature is an interactive user simulator that reproduces requirement clarification, feedback, and project iteration for training and evaluation. Custom sparse attention supports these long coding and agent runs.
MiniMax describes M3 as the new generation after MiniMax M2.7, explicitly called the stable point release of the previous line. Thinking can be toggled, with the API and released weights as separate access paths. The model identity therefore combines coding, agent work, and native multimodality.
- Position
- Rank 36 of 91
- Index score
- 16.9 / 100
Methodology and source
The LLM comparison hub's selected-panel index averages rank percentiles from 65 documented comparison cohorts. Benchmark meta-scores are shown in the benchmark section.
Benchmark meta-analysis
Overall and area scores
These Gradually indexes place selected published measurements on a 0 to 100 scale. They are not accuracy percentages and do not guarantee results in your application.
Retrieval dates of the sources used 2026-10-15 - 2026-10-19
Overall index
Index 16.9 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Standard error
- ± 3.8
- 95% interval
- 10.5 to 25.5
- Test series
- 40
- Test families
- 33 / 65
- Sources
- 2
- Share of the fixed test panel (informative)
- 47 %
Coding
Index 6.0 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Standard error
- ± 2.2
- 95% interval
- 2.7 to 11.7
- Test series
- 11
- Test families
- 8 / 15
- Sources
- 2
- Share of the fixed test panel (informative)
- 47 %
Reasoning
Index 26.0 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Standard error
- ± 9.1
- 95% interval
- 11.7 to 46.3
- Test series
- 4
- Test families
- 4 / 7
- Sources
- 2
- Share of the fixed test panel (informative)
- 43 %
Mathematics
Index 9.7 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Standard error
- ± 1.5
- 95% interval
- 7.1 to 12.9
- Test series
- 1
- Test families
- 1 / 5
- Sources
- 1
- Share of the fixed test panel (informative)
- 20 %
Knowledge
Index 7.4 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Standard error
- ± 3.5
- 95% interval
- 2.7 to 16.8
- Test series
- 2
- Test families
- 2 / 3
- Sources
- 2
- Share of the fixed test panel (informative)
- 67 %
Agents
Index 10.1 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Standard error
- ± 8.7
- 95% interval
- 1.3 to 37.8
- Test series
- 5
- Test families
- 5 / 12
- Sources
- 2
- Share of the fixed test panel (informative)
- 42 %
General
Index 38.8 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Standard error
- ± 7.8
- 95% interval
- 24.7 to 54.6
- Test series
- 1
- Test families
- 1 / 5
- Sources
- 1
- Share of the fixed test panel (informative)
- 20 %
Finance
Index 24.7 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Standard error
- ± 6.0
- 95% interval
- 14.5 to 37.8
- Test series
- 6
- Test families
- 6 / 7
- Sources
- 1
- Share of the fixed test panel (informative)
- 86 %
Legal
Index 31.9 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Standard error
- ± 5.3
- 95% interval
- 22.3 to 43.0
- Test series
- 3
- Test families
- 3 / 4
- Sources
- 1
- Share of the fixed test panel (informative)
- 75 %
Health
Index 35.7 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Standard error
- ± 8.2
- 95% interval
- 21.3 to 52.5
- Test series
- 2
- Test families
- 2 / 3
- Sources
- 1
- Share of the fixed test panel (informative)
- 67 %
Cybersecurity
Index 19.4 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Standard error
- ± 6.0
- 95% interval
- 9.9 to 33.0
- Test series
- 1
- Test families
- 1 / 1
- Sources
- 1
- Share of the fixed test panel (informative)
- 100 %
Multimodal
Index 10.2 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Standard error
- ± 1.8
- 95% interval
- 7.1 to 14.1
- Test series
- 2
- Test families
- 1 / 4
- Sources
- 2
- Share of the fixed test panel (informative)
- 25 %
Productivity
Index 34.2 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Standard error
- ± 4.4
- 95% interval
- 26.0 to 43.2
- Test series
- 1
- Test families
- 1 / 2
- Sources
- 1
- Share of the fixed test panel (informative)
- 50 %
Education
Index 36.5 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Standard error
- ± 10.3
- 95% interval
- 18.9 to 57.5
- Test series
- 1
- Test families
- 1 / 2
- Sources
- 1
- Share of the fixed test panel (informative)
- 50 %
Documented method · Included test families and measurements
Method version: benchmark-meta-score-v3
The index includes active measurements from reviewed primary sources when at least five models are compared in the same documented comparison slice across dataset, harness, agent, tools, and trial count. Each benchmark series and evaluator contributes one shared setup slice from the newest capture. When one source and series include several explicitly documented reasoning tiers, the highest documented tier (none through max) is selected, never the best result value. The explicit source label “Non-reasoning” is treated as none. Unknown or ambiguous tiers exclude the model from that series. Within each series, percentages and rates are logit-transformed, other units stay unchanged, and all values are then standardized. A one-factor model then estimates one shared strength per model and, per series, how sharply it separates the models. Area scores move away from that strength only as far as the model's own results in the area support. The overall score weights the core areas at 75% and finance, law and health at 25%. It requires at least eight test series from two sources and three areas. The 0 to 100 scale refers to a fixed reference group of 29 language models whose average sits at 50.
Published model-specific parameters can differ. This is not a controlled experiment; comparisons with such differences are marked provisional.
Unmeasured series are not entered as zero. Where a model has no own results in a core area, its overall strength stands in, and the note “estimated without own results in …” names the area. Fewer test series lead to a larger standard error.
The 95% interval follows from the standard error of 200 recalculations with randomly redrawn test families. It describes how precisely the recorded test series determine the value. It is no prediction for future tasks or for later recalculations with other participants.
The source count is not a count of independent experiments.
OECD handbook on composite indicatorsAll 36 test families and 12 of 40 raw measurements are listed here. The complete calculation for every model is available in the JSON export.
Test family: AA-AnalystAgent
Agents · Mean rank percentile of the family: 7.9 / 100Family weight in the fixed test panel (informative): 0.89 % · Coverage of this test family: 100 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-aa-analyst-agent
- Series weight within the test family:
- 100 %
- Nominal contribution to the overall panel:
- 0.89 %
- Raw value:
- 10 %
- Metric:
- pass^5 reliability
- Version:
- AA cohort: 80 questions
- Participating models:
- 39
- Rank percentile within the cohort:
- 7.9 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-aa-analyst-agent:AA cohort: 80 questions:standalone:reasoning:tokens=2000:suffix=unspecified
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-aa-analyst-agent","AA cohort: 80 questions","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Harness:
- Artificial Analysis Stirrup
- Agent:
- Stirrup analyst agent
- Tool policy:
- 100-turn cap; Python sandbox with source files, URL fetch, image viewing, and answer submission
- Attempts:
- pass^5, 5 independent attempts per question
- Setup and model parameters
- Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption. 80 quantitative questions across 14 domains are run five independent times. pass^5 counts only questions answered correctly in all five attempts.. Harness: Artificial Analysis Stirrup. Agent: Stirrup analyst agent. Tool policy: 100-turn cap; Python sandbox with source files, URL fetch, image viewing, and answer submission. Attempts: pass^5, 5 independent attempts per question. Reasoning: reasoning enabled
Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption. 80 quantitative questions across 14 domains are run five independent times. pass^5 counts only questions answered correctly in all five attempts.. Source model ID: artificial-analysis/277f939a-985b-4b37-859d-b3eabc7c0b26/minimax-m3/minimax-m3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Model snapshot: MiniMax-M3. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Harness: Artificial Analysis Stirrup. Agent: Stirrup analyst agent. Tool policy: 100-turn cap; Python sandbox with source files, URL fetch, image viewing, and answer submission. Attempts: pass^5, 5 independent attempts per question. Reasoning: reasoning enabled. Score display: 10.0%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: AA-Briefcase
Agents · Mean rank percentile of the family: 61.0 / 100Family weight in the fixed test panel (informative): 0.89 % · Coverage of this test family: 100 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-aa-briefcase
- Series weight within the test family:
- 100 %
- Nominal contribution to the overall panel:
- 0.89 %
- Raw value:
- 1,090.37 Elo
- Metric:
- AA-Briefcase Elo
- Version:
- v1.1
- Participating models:
- 83
- Rank percentile within the cohort:
- 61.0 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-aa-briefcase:v1.1:v4.3.2:reasoning:tokens=2000:suffix=unspecified
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-aa-briefcase","v1.1","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Setup and model parameters
- Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Reasoning: reasoning enabled
Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Source model ID: artificial-analysis/277f939a-985b-4b37-859d-b3eabc7c0b26/minimax-m3/minimax-m3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Model snapshot: MiniMax-M3. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: AA-LCR
Reasoning · Mean rank percentile of the family: 88.4 / 100Family weight in the fixed test panel (informative): 1.53 % · Coverage of this test family: 100 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-aa-lcr
- Series weight within the test family:
- 100 %
- Nominal contribution to the overall panel:
- 1.53 %
- Raw value:
- 83 %
- Metric:
- Pass rate
- Version:
- v1.1
- Participating models:
- 83
- Rank percentile within the cohort:
- 88.4 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-aa-lcr:v1.1:v4.3.2:reasoning:tokens=2000:suffix=unspecified
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-aa-lcr","v1.1","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Setup and model parameters
- Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Reasoning: reasoning enabled
Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Source model ID: artificial-analysis/277f939a-985b-4b37-859d-b3eabc7c0b26/minimax-m3/minimax-m3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Model snapshot: MiniMax-M3. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 83.0%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: AutomationBench-AA
Agents · Mean rank percentile of the family: 52.4 / 100Family weight in the fixed test panel (informative): 0.89 % · Coverage of this test family: 100 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-automationbench-aa
- Series weight within the test family:
- 100 %
- Nominal contribution to the overall panel:
- 0.89 %
- Raw value:
- 21.25125760074941 %
- Metric:
- Objectives completed without guardrail violations
- Version:
- unspecified
- Participating models:
- 83
- Rank percentile within the cohort:
- 52.4 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-automationbench-aa:unspecified:v4.3.2:reasoning:tokens=2000:suffix=unspecified
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-automationbench-aa","unspecified","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Setup and model parameters
- Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Reasoning: reasoning enabled
Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Source model ID: artificial-analysis/277f939a-985b-4b37-859d-b3eabc7c0b26/minimax-m3/minimax-m3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Model snapshot: MiniMax-M3. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 21.3%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: FrontierCode 1.1 Main
Coding · Mean rank percentile of the family: 6.7 / 100Family weight in the fixed test panel (informative): 0.71 % · Coverage of this test family: 100 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-frontiercode
- Series weight within the test family:
- 100 %
- Nominal contribution to the overall panel:
- 0.71 %
- Raw value:
- 23.0037666666667 %
- Metric:
- Mean score over three attempts per task
- Version:
- 1.1 Main
- Participating models:
- 16
- Rank percentile within the cohort:
- 6.7 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-frontiercode:1.1 Main:standalone:reasoning:tokens=2000:suffix=unspecified
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-frontiercode","1.1 Main","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Harness:
- Artificial Analysis Stirrup
- Agent:
- Stirrup coding agent
- Tool policy:
- 250-turn cap; repository worktree graded as left by the agent
- Attempts:
- Mean score, 3 attempts per task
- Setup and model parameters
- Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption. The primary 100-task FrontierCode 1.1 set is run three times per task, with equal task weights. Failing any blocking check or being flagged by the trajectory scanner scores zero; runs passing every blocking check score 70 to 100 percent.. Harness: Artificial Analysis Stirrup. Agent: Stirrup coding agent. Tool policy: 250-turn cap; repository worktree graded as left by the agent. Attempts: Mean score, 3 attempts per task. Reasoning: reasoning enabled
Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption. The primary 100-task FrontierCode 1.1 set is run three times per task, with equal task weights. Failing any blocking check or being flagged by the trajectory scanner scores zero; runs passing every blocking check score 70 to 100 percent.. Source model ID: artificial-analysis/277f939a-985b-4b37-859d-b3eabc7c0b26/minimax-m3/minimax-m3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Model snapshot: MiniMax-M3. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Harness: Artificial Analysis Stirrup. Agent: Stirrup coding agent. Tool policy: 250-turn cap; repository worktree graded as left by the agent. Attempts: Mean score, 3 attempts per task. Reasoning: reasoning enabled. Score display: 23.0%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: GDP.pdf
Reasoning · Mean rank percentile of the family: 42.7 / 100Family weight in the fixed test panel (informative): 1.53 % · Coverage of this test family: 100 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-gdp-pdf
- Series weight within the test family:
- 100 %
- Nominal contribution to the overall panel:
- 1.53 %
- Raw value:
- 9.8 %
- Metric:
- All-pass rate
- Version:
- unspecified
- Participating models:
- 83
- Rank percentile within the cohort:
- 42.7 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-gdp-pdf:unspecified:v4.3.2:reasoning:tokens=2000:suffix=unspecified
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-gdp-pdf","unspecified","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Setup and model parameters
- Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Reasoning: reasoning enabled
Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Source model ID: artificial-analysis/277f939a-985b-4b37-859d-b3eabc7c0b26/minimax-m3/minimax-m3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Model snapshot: MiniMax-M3. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 9.8%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: GDPval-AA
Agents · Mean rank percentile of the family: 59.8 / 100Family weight in the fixed test panel (informative): 0.89 % · Coverage of this test family: 100 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-gdpval-aa
- Series weight within the test family:
- 100 %
- Nominal contribution to the overall panel:
- 0.89 %
- Raw value:
- 1,242.47 Elo
- Metric:
- GDPval-AA Elo
- Version:
- v2.1
- Participating models:
- 83
- Rank percentile within the cohort:
- 59.8 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-gdpval-aa:v2.1:v4.3.2:reasoning:tokens=2000:suffix=unspecified
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-gdpval-aa","v2.1","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Setup and model parameters
- Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Reasoning: reasoning enabled
Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Source model ID: artificial-analysis/277f939a-985b-4b37-859d-b3eabc7c0b26/minimax-m3/minimax-m3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Model snapshot: MiniMax-M3. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: IFBench
General · Mean rank percentile of the family: 100.0 / 100Family weight in the fixed test panel (informative): 2.14 % · Coverage of this test family: 100 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-ifbench
- Series weight within the test family:
- 100 %
- Nominal contribution to the overall panel:
- 2.14 %
- Raw value:
- 82.85714285714289 %
- Metric:
- IFBench prompt-level loose accuracy (pass@1)
- Version:
- AA test set: 294 questions
- Participating models:
- 70
- Rank percentile within the cohort:
- 100.0 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-ifbench:AA test set: 294 questions:standalone:reasoning:tokens=2000:suffix=unspecified
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-ifbench","AA test set: 294 questions","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Tool policy:
- Single-turn answer evaluated with the official IFBench source code
- Attempts:
- pass@1, 5 repeats per question
- Setup and model parameters
- Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: reasoning enabled
Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Source model ID: artificial-analysis/277f939a-985b-4b37-859d-b3eabc7c0b26/minimax-m3/minimax-m3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Model snapshot: MiniMax-M3. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: reasoning enabled. Score display: 82.9%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: AA-Omniscience
Knowledge · Mean rank percentile of the family: 58.5 / 100Family weight in the fixed test panel (informative): 3.57 % · Coverage of this test family: 100 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-omniscience
- Series weight within the test family:
- 100 %
- Nominal contribution to the overall panel:
- 3.57 %
- Raw value:
- 1.35 points
- Metric:
- AA-Omniscience Index
- Version:
- unspecified
- Participating models:
- 83
- Rank percentile within the cohort:
- 58.5 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-omniscience:unspecified:v4.3.2:reasoning:tokens=2000:suffix=unspecified
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-omniscience","unspecified","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Setup and model parameters
- Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Reasoning: reasoning enabled
Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Source model ID: artificial-analysis/277f939a-985b-4b37-859d-b3eabc7c0b26/minimax-m3/minimax-m3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Model snapshot: MiniMax-M3. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: GPQA Diamond
Reasoning · Mean rank percentile of the family: 82.2 / 100Family weight in the fixed test panel (informative): 1.53 % · Coverage of this test family: 50 %
- Vals AI
Published configurations differ within this cohort.
- Measurement:
- vals-gpqa
- Series weight within the test family:
- 50 %
- Nominal contribution to the overall panel:
- 0.77 %
- Raw value:
- 92.676 %
- Metric:
- accuracy
- Version:
- 1
- Participating models:
- 77
- Rank percentile within the cohort:
- 82.2 %
- Retrieved:
- 2026-10-15
- Comparison cohort:
- vals-gpqa:1:overall
- Documented comparison setup
- Publication cohort:
- vals-gpqa:1:overall
- Dataset type:
- public
- Setup and model parameters
- Temperature: 1. Top P: 0.95. Maximum output tokens: 512000
Source model ID: minimax/MiniMax-M3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Temperature: 1. Top P: 0.95. Maximum output tokens: 512000. Latency in seconds: 278.908. Standard error: 1.443. Cost per task in USD: 0.0255. Source ID: vals-ai. Evidence capture ID: vals-gpqa-2026-10-15-951eb5224097. Source payload hash: 951eb5224097733a9d09d06c14908ae2980e2e640e539f2c284877c5092d7077. Parser version: vals-astro-v3. Imported at: 2026-10-15
- Vals AI
Test family: Humanity’s Last Exam
Reasoning · Mean rank percentile of the family: 61.0 / 100Family weight in the fixed test panel (informative): 1.53 % · Coverage of this test family: 50 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-humanitys-last-exam
- Series weight within the test family:
- 50 %
- Nominal contribution to the overall panel:
- 0.77 %
- Raw value:
- 38.9712696941613 %
- Metric:
- Text-only pass@1 accuracy
- Version:
- unspecified
- Participating models:
- 83
- Rank percentile within the cohort:
- 61.0 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-humanitys-last-exam:unspecified:v4.3.2:reasoning:tokens=2000:suffix=unspecified
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-humanitys-last-exam","unspecified","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Setup and model parameters
- Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Reasoning: reasoning enabled
Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Source model ID: artificial-analysis/277f939a-985b-4b37-859d-b3eabc7c0b26/minimax-m3/minimax-m3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Model snapshot: MiniMax-M3. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 39.0%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: MMMU-Pro
Multimodal · Mean rank percentile of the family: 50.8 / 100Family weight in the fixed test panel (informative): 2.68 % · Coverage of this test family: 100 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-mmmu-pro
- Series weight within the test family:
- 50 %
- Nominal contribution to the overall panel:
- 1.34 %
- Raw value:
- 78.5549132947977 %
- Metric:
- pass@1 accuracy
- Version:
- AA cohort: 1,730 questions
- Participating models:
- 57
- Rank percentile within the cohort:
- 63.4 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-mmmu-pro:AA cohort: 1,730 questions:standalone:reasoning:tokens=2000:suffix=unspecified
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-mmmu-pro","AA cohort: 1,730 questions","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Tool policy:
- Ten-option multiple choice; regex answer extraction
- Attempts:
- pass@1, one run per question
- Setup and model parameters
- Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption. The AA run covers 1,730 questions with ten answer options. Answers are extracted by regex and scored pass@1.. Tool policy: Ten-option multiple choice; regex answer extraction. Attempts: pass@1, one run per question. Reasoning: reasoning enabled
Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption. The AA run covers 1,730 questions with ten answer options. Answers are extracted by regex and scored pass@1.. Source model ID: artificial-analysis/277f939a-985b-4b37-859d-b3eabc7c0b26/minimax-m3/minimax-m3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Model snapshot: MiniMax-M3. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Ten-option multiple choice; regex answer extraction. Attempts: pass@1, one run per question. Reasoning: reasoning enabled. Score display: 78.6%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: SWE-bench Verified
Coding · Mean rank percentile of the family: 45.8 / 100Family weight in the fixed test panel (informative): 0.71 % · Coverage of this test family: 50 %
Test family: Terminal-Bench
Coding · Mean rank percentile of the family: 44.8 / 100Family weight in the fixed test panel (informative): 0.71 % · Coverage of this test family: 100 %
Test family: Terminal-Bench Science
Coding · Mean rank percentile of the family: 15.2 / 100Family weight in the fixed test panel (informative): 0.71 % · Coverage of this test family: 50 %
Test family: Code Migration
Coding · Mean rank percentile of the family: 35.5 / 100Family weight in the fixed test panel (informative): 0.71 % · Coverage of this test family: 100 %
Test family: CorpFin v2
Finance · Mean rank percentile of the family: 89.2 / 100Family weight in the fixed test panel (informative): 1.19 % · Coverage of this test family: 100 %
Test family: CyberBench v1.1
Cybersecurity · Mean rank percentile of the family: 39.4 / 100Family weight in the fixed test panel (informative): 0 % · Coverage of this test family: 100 %
Test family: EMB
Finance · Mean rank percentile of the family: 27.1 / 100Family weight in the fixed test panel (informative): 1.19 % · Coverage of this test family: 100 %
Test family: Finance Agent (v2)
Finance · Mean rank percentile of the family: 40.0 / 100Family weight in the fixed test panel (informative): 1.19 % · Coverage of this test family: 100 %
Test family: LiveCodeBench v6
Coding · Mean rank percentile of the family: 49.4 / 100Family weight in the fixed test panel (informative): 0.71 % · Coverage of this test family: 100 %
Test family: Harvey's Legal Agent Benchmark
Legal · Mean rank percentile of the family: 59.0 / 100Family weight in the fixed test panel (informative): 2.08 % · Coverage of this test family: 100 %
Test family: LegalBench
Legal · Mean rank percentile of the family: 79.5 / 100Family weight in the fixed test panel (informative): 2.08 % · Coverage of this test family: 100 %
Test family: Legal Research Bench
Legal · Mean rank percentile of the family: 43.3 / 100Family weight in the fixed test panel (informative): 2.08 % · Coverage of this test family: 100 %
Test family: MedCode
Health · Mean rank percentile of the family: 59.7 / 100Family weight in the fixed test panel (informative): 2.78 % · Coverage of this test family: 100 %
Test family: MedScribe
Health · Mean rank percentile of the family: 82.4 / 100Family weight in the fixed test panel (informative): 2.78 % · Coverage of this test family: 100 %
Test family: MMLU-Pro
Knowledge · Mean rank percentile of the family: 41.6 / 100Family weight in the fixed test panel (informative): 3.57 % · Coverage of this test family: 100 %
Test family: MortgageTax
Finance · Mean rank percentile of the family: 76.9 / 100Family weight in the fixed test panel (informative): 1.19 % · Coverage of this test family: 100 %
Test family: ProofBench
Mathematics · Mean rank percentile of the family: 23.1 / 100Family weight in the fixed test panel (informative): 2.14 % · Coverage of this test family: 100 %
Test family: SAGE
Education · Mean rank percentile of the family: 79.3 / 100Family weight in the fixed test panel (informative): 0 % · Coverage of this test family: 100 %
Test family: SkillsBench
Agents · Mean rank percentile of the family: 48.3 / 100Family weight in the fixed test panel (informative): 0.89 % · Coverage of this test family: 100 %
Test family: Public Benefits Bench v1.1
Productivity · Mean rank percentile of the family: 55.3 / 100Family weight in the fixed test panel (informative): 0 % · Coverage of this test family: 100 %
Test family: Tax Agent Bench
Finance · Mean rank percentile of the family: 40.0 / 100Family weight in the fixed test panel (informative): 1.19 % · Coverage of this test family: 100 %
Test family: TaxEval v2
Finance · Mean rank percentile of the family: 50.0 / 100Family weight in the fixed test panel (informative): 1.19 % · Coverage of this test family: 100 %
Test family: Vibe Code Bench 1-100
Coding · Mean rank percentile of the family: 9.5 / 100Family weight in the fixed test panel (informative): 0.71 % · Coverage of this test family: 100 %
Test family: Vibe Code Bench v1.1
Coding · Mean rank percentile of the family: 43.1 / 100Family weight in the fixed test panel (informative): 0.71 % · Coverage of this test family: 100 %
Benchmark sources at a glance
Each evaluator measures different capabilities under its own conditions. Test series, composite indices and their components stay separate. The detailed results below retain their scales, configurations and source dates.
| Evaluator | Test series | Composite indices | Recorded active measurements |
|---|---|---|---|
| Artificial Analysis | 13 | 1 | 26 |
| Vals AI | 28 | 2 | 205 |
Coverage is not a quality ranking. Overlapping tests and multiple settings do not count as independent experiments. Vendor claims, historical and disputed results are excluded from this overview and remain labelled in the detailed evidence.
7 measurements from these sources still lack a verified test-family identity and do not increase the test-series count.
Page 1 of 20
Published benchmarks
Taste-Bench
Overall
502 technical decision points from engineering and research workflows. Each choice is presented in both answer orders. The overall score averages engineering and research and requires both answer orders to be correct. Unparseable responses count as wrong. Reasoning settings and output budget are part of the setup.
Note (MiniMax M3): 3 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
1.GPT-5.6 Sol59.7%
Note: 0 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
2.GPT-5.559.5%
Note: 0 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
3.Claude Opus 555.5%
Note: 0 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
4.Grok 4.554.6%
Note: 10 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
5.GPT-5.6 Terra54%
Note: 0 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
6.GLM-5.253.9%
Note: 17 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
7.Claude Sonnet 551.6%
Note: 0 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
8.GPT-5.6 Luna49%
Note: 0 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
10.DeepSeek-V4-Flash43.3%
Note: 2 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
11.GPT-5.4 mini40.1%
Note: 112 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
12.Mistral Medium 3.537.7%
Note: 24 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
13.GPT-5.4 nano36.6%
Note: 93 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
14.Grok 4.20 Reasoning15.7%
Note: 459 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
higher is betterAs of September 26, 2026Scale: 0% - 100%
Methodology and context
- Comparison cohort
- taste-bench-paper-v2-502
- Metric
- both-orders-correct, engineering/research macro average
- Scale
- 0-100
- Participants
- 14
- Methodology and context
- Same prompt for all models. Each of 502 questions is shown twice with the options reversed. Average of engineering and research success rates, requiring both orders to be correct. 65,536-token output budget; unparseable answers count as wrong.. Source model ID: curated/minimax-m3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Evaluator: Taste-Bench paper. Dataset type: public. Leaderboard date: 2026-09-23. Attempts: 502 questions, two option orders each. Reasoning effort: default. Maximum output tokens: 65536. Source ID: taste-bench-paper. Evidence capture ID: curated-taste-bench-paper-2026-09-26-3a33ce33758a. Source payload hash: 3a33ce33758afc5b08eb5151c8d63e4b8f05059485c9e773ba86bba88c22f152. Parser version: curated-v1. Imported at: 2026-10-15
Health
MedCode
Overall
higher is betterAs of October 15, 2026Scale: 0% - 100%
Methodology and context
- Comparison cohort
- vals-medcode:1:overall
- Metric
- accuracy
- Scale
- 0-100
- Participants
- 10
- Methodology and context
- Source model ID: minimax/MiniMax-M3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-13. Temperature: 1. Top P: 0.95. Maximum output tokens: 30000. Latency in seconds: 63.12. Standard error: 2.104. Cost per task in USD: 0.012125. Source ID: vals-ai. Evidence capture ID: vals-medcode-2026-10-15-988a6ae1e07e. Source payload hash: 988a6ae1e07e33ce031572ed4a804be11c36ee97a1dd75cbe4740fff3b534f8c. Parser version: vals-astro-v3. Imported at: 2026-10-15
MedScribe
Overall
higher is betterAs of October 15, 2026Scale: 0% - 100%
Methodology and context
- Comparison cohort
- vals-medscribe:1:overall
- Metric
- accuracy
- Scale
- 0-100
- Participants
- 10
- Methodology and context
- Source model ID: minimax/MiniMax-M3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-13. Temperature: 1. Top P: 0.95. Maximum output tokens: 30000. Latency in seconds: 123.967. Standard error: 1.957. Cost per task in USD: 0.013748. Source ID: vals-ai. Evidence capture ID: vals-medscribe-2026-10-15-271fc122ddc2. Source payload hash: 271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0. Parser version: vals-astro-v3. Imported at: 2026-10-15
Education
SAGE
| Sub-task | MiniMax M3 (This model) | Grok 4.20 Reasoning | Qwen 3.6 27B | Grok 4.3 | MiMo-V2.5 |
|---|---|---|---|---|---|
| Automata | 37.3% | 40.48% (best value in this row) | 35.71% | 35.32% | 29.76% |
| Linear Algebra | 66.8% (best value in this row) | 39.33% | 59.75% | 18.33% | 58.76% |
| Overall | 50.57% (best value in this row) | 38.24% | 45.58% | 19.74% | 43.27% |
| Partial Differential Equations | 47.62% (best value in this row) | 34.92% | 41.27% | 5.56% | 41.27% |
higher is betterAs of October 15, 2026Source: Vals AIbars scaled within each row, not across rows
Methodology and context
- Metric
- accuracy
Vals Multimodal Index
SWE-bench
higher is betterAs of October 15, 2026Scale: 0% - 100%
Methodology and context
- Comparison cohort
- vals-vals-multimodal-index:1.2:swebench
- Metric
- benchmark score
- Scale
- 0-100
- Participants
- 29
- Methodology and context
- Source model ID: minimax/MiniMax-M3. Source model name: MiniMax M3. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-08-11. Latency in seconds: 765.232. Standard error: 4.554. Cost per task in USD: 0.508278. Source ID: vals-ai. Evidence capture ID: vals-vals_multimodal_index-2026-10-15-077b22575f6e. Source payload hash: 077b22575f6e075b7b78157d000ec8f94d7ead409c7dcbcf04887630ed572a2d. Parser version: vals-astro-v3. Imported at: 2026-10-15
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.
AA-AnalystAgent: Overall (Show measurement, test conditions, and source)
- Source value
- 10
- Score
- 10
- Metric
- pass^5 reliability
- Unit
- %
- Benchmark version
- AA cohort: 80 questions
- Category
- agentic
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- artificial-analysis-aa-analyst-agent:AA cohort: 80 questions:standalone:reasoning:tokens=2000:suffix=unspecified
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption. 80 quantitative questions across 14 domains are run five independent times. pass^5 counts only questions answered correctly in all five attempts.. Source model ID: artificial-analysis/277f939a-985b-4b37-859d-b3eabc7c0b26/minimax-m3/minimax-m3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Model snapshot: MiniMax-M3. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Harness: Artificial Analysis Stirrup. Agent: Stirrup analyst agent. Tool policy: 100-turn cap; Python sandbox with source files, URL fetch, image viewing, and answer submission. Attempts: pass^5, 5 independent attempts per question. Reasoning: reasoning enabled. Score display: 10.0%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Comparison methodology
- Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption. 80 quantitative questions across 14 domains are run five independent times. pass^5 counts only questions answered correctly in all five attempts.. Harness: Artificial Analysis Stirrup. Agent: Stirrup analyst agent. Tool policy: 100-turn cap; Python sandbox with source files, URL fetch, image viewing, and answer submission. Attempts: pass^5, 5 independent attempts per question. Reasoning: reasoning enabled
- Context
- Questions, source files, and reference answers are private. pass^5 measures reliability across all five attempts, not pass@1.
AA-LCR: Overall (Show measurement, test conditions, and source)
- Source value
- 83
- Score
- 83
- Metric
- Pass rate
- Unit
- %
- Benchmark version
- v1.1
- Category
- reasoning
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- artificial-analysis-aa-lcr:v1.1:v4.3.2:reasoning:tokens=2000:suffix=unspecified
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Source model ID: artificial-analysis/277f939a-985b-4b37-859d-b3eabc7c0b26/minimax-m3/minimax-m3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Model snapshot: MiniMax-M3. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 83.0%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Comparison methodology
- Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Reasoning: reasoning enabled
AutomationBench-AA: Overall (Show measurement, test conditions, and source)
- Source value
- 21.25125760074941
- Score
- 21.25125760074941
- Metric
- Objectives completed without guardrail violations
- Unit
- %
- Benchmark version
- unspecified
- Category
- agentic
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- artificial-analysis-automationbench-aa:unspecified:v4.3.2:reasoning:tokens=2000:suffix=unspecified
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Source model ID: artificial-analysis/277f939a-985b-4b37-859d-b3eabc7c0b26/minimax-m3/minimax-m3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Model snapshot: MiniMax-M3. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 21.3%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Comparison methodology
- Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Reasoning: reasoning enabled
CritPt: Overall (Show measurement, test conditions, and source)
- Source value
- 3.7142857142857104
- Score
- 3.7142857142857104
- Metric
- Score
- Unit
- %
- Benchmark version
- unspecified
- Category
- reasoning
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- artificial-analysis-critpt:unspecified:v4.3.2:reasoning:tokens=2000:suffix=unspecified
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- disputed
- Retrieved at
- 2026-10-19
- Methodology
- Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Source model ID: artificial-analysis/277f939a-985b-4b37-859d-b3eabc7c0b26/minimax-m3/minimax-m3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Model snapshot: MiniMax-M3. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 3.7%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Comparison methodology
- Exact AA configuration: MiniMax-M3 (release minimax-m3, row minimax-m3, UUID 277f939a-985b-4b37-859d-b3eabc7c0b26, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Reasoning: reasoning enabled
- Context
- Artificial Analysis marks CritPt as under review; dataset revisions may change results.. The source dataset marks this result as disputed. It remains visible as documented evidence, but is not reliable comparative proof.
Recorded measurement details
Taste-Bench: Overall (Show measurement, test conditions, and source)
- Source value
- 45.3
- Score
- 45.3
- Metric
- both-orders-correct, engineering/research macro average
- Unit
- %
- Benchmark version
- arxiv:2609.25804v2
- Category
- agentic
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- taste-bench-paper-v2-502
- Source type
- independent-evaluator
- Evaluator
- Taste-Bench paper
- Status
- active
- Retrieved at
- 2026-09-26
- Methodology
- Same prompt for all models. Each of 502 questions is shown twice with the options reversed. Average of engineering and research success rates, requiring both orders to be correct. 65,536-token output budget; unparseable answers count as wrong.. Source model ID: curated/minimax-m3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Evaluator: Taste-Bench paper. Dataset type: public. Leaderboard date: 2026-09-23. Attempts: 502 questions, two option orders each. Reasoning effort: default. Maximum output tokens: 65536. Source ID: taste-bench-paper. Evidence capture ID: curated-taste-bench-paper-2026-09-26-3a33ce33758a. Source payload hash: 3a33ce33758afc5b08eb5151c8d63e4b8f05059485c9e773ba86bba88c22f152. Parser version: curated-v1. Imported at: 2026-10-15
- Comparison methodology
- Same prompt for all models. Each of 502 questions is shown twice with the options reversed. Average of engineering and research success rates, requiring both orders to be correct. 65,536-token output budget; unparseable answers count as wrong.
- Context
- 3 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
MedCode: Overall (Show measurement, test conditions, and source)
- Source value
- 46.289
- Score
- 46.289
- Metric
- accuracy
- Unit
- %
- Benchmark version
- 1
- Category
- health
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- vals-medcode:1:overall
- Source type
- independent-evaluator
- Evaluator
- Vals AI
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Source model ID: minimax/MiniMax-M3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-13. Temperature: 1. Top P: 0.95. Maximum output tokens: 30000. Latency in seconds: 63.12. Standard error: 2.104. Cost per task in USD: 0.012125. Source ID: vals-ai. Evidence capture ID: vals-medcode-2026-10-15-988a6ae1e07e. Source payload hash: 988a6ae1e07e33ce031572ed4a804be11c36ee97a1dd75cbe4740fff3b534f8c. Parser version: vals-astro-v3. Imported at: 2026-10-15
- Comparison methodology
- Temperature: 1. Top P: 0.95. Maximum output tokens: 30000
MedScribe: Overall (Show measurement, test conditions, and source)
- Source value
- 87.252
- Score
- 87.252
- Metric
- accuracy
- Unit
- %
- Benchmark version
- 1
- Category
- health
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- vals-medscribe:1:overall
- Source type
- independent-evaluator
- Evaluator
- Vals AI
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Source model ID: minimax/MiniMax-M3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-13. Temperature: 1. Top P: 0.95. Maximum output tokens: 30000. Latency in seconds: 123.967. Standard error: 1.957. Cost per task in USD: 0.013748. Source ID: vals-ai. Evidence capture ID: vals-medscribe-2026-10-15-271fc122ddc2. Source payload hash: 271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0. Parser version: vals-astro-v3. Imported at: 2026-10-15
- Comparison methodology
- Temperature: 1. Top P: 0.95. Maximum output tokens: 30000
SAGE: Automata (Show measurement, test conditions, and source)
- Source value
- 37.302
- Score
- 37.302
- Metric
- accuracy
- Unit
- %
- Benchmark version
- 1
- Category
- education
- Task
- automata
- Task label
- Automata
- Direction
- Higher is better
- Comparison cohort
- vals-sage:1:automata
- Source type
- independent-evaluator
- Evaluator
- Vals AI
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Source model ID: minimax/MiniMax-M3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-08. Temperature: 1. Top P: 0.95. Maximum output tokens: 30000. Latency in seconds: 115.085. Standard error: 6.222. Cost per task in USD: 0.020054. Source ID: vals-ai. Evidence capture ID: vals-sage-2026-10-15-cc5fb3fecdb0. Source payload hash: cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c. Parser version: vals-astro-v3. Imported at: 2026-10-15
- Comparison methodology
- Temperature: 1. Top P: 0.95. Maximum output tokens: 30000
SAGE: Linear Algebra (Show measurement, test conditions, and source)
- Source value
- 66.802
- Score
- 66.802
- Metric
- accuracy
- Unit
- %
- Benchmark version
- 1
- Category
- education
- Task
- linear_algebra
- Task label
- Linear Algebra
- Direction
- Higher is better
- Comparison cohort
- vals-sage:1:linear_algebra
- Source type
- independent-evaluator
- Evaluator
- Vals AI
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Source model ID: minimax/MiniMax-M3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-08. Temperature: 1. Top P: 0.95. Maximum output tokens: 30000. Latency in seconds: 96.704. Standard error: 5.314. Cost per task in USD: 0.034489. Source ID: vals-ai. Evidence capture ID: vals-sage-2026-10-15-cc5fb3fecdb0. Source payload hash: cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c. Parser version: vals-astro-v3. Imported at: 2026-10-15
- Comparison methodology
- Temperature: 1. Top P: 0.95. Maximum output tokens: 30000
SAGE: Overall (Show measurement, test conditions, and source)
- Source value
- 50.574
- Score
- 50.574
- Metric
- accuracy
- Unit
- %
- Benchmark version
- 1
- Category
- education
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- vals-sage:1:overall
- Source type
- independent-evaluator
- Evaluator
- Vals AI
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Source model ID: minimax/MiniMax-M3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-08. Temperature: 1. Top P: 0.95. Maximum output tokens: 30000. Latency in seconds: 118.538. Standard error: 3.436. Cost per task in USD: 0.025844. Source ID: vals-ai. Evidence capture ID: vals-sage-2026-10-15-cc5fb3fecdb0. Source payload hash: cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c. Parser version: vals-astro-v3. Imported at: 2026-10-15
- Comparison methodology
- Temperature: 1. Top P: 0.95. Maximum output tokens: 30000
SAGE: Partial Differential Equations (Show measurement, test conditions, and source)
- Source value
- 47.619
- Score
- 47.619
- Metric
- accuracy
- Unit
- %
- Benchmark version
- 1
- Category
- education
- Task
- PDEs
- Task label
- Partial Differential Equations
- Direction
- Higher is better
- Comparison cohort
- vals-sage:1:PDEs
- Source type
- independent-evaluator
- Evaluator
- Vals AI
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Source model ID: minimax/MiniMax-M3. Source model name: MiniMax M3. Provider reported by source: MiniMax. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-08. Temperature: 1. Top P: 0.95. Maximum output tokens: 30000. Latency in seconds: 143.824. Standard error: 6.27. Cost per task in USD: 0.022988. Source ID: vals-ai. Evidence capture ID: vals-sage-2026-10-15-cc5fb3fecdb0. Source payload hash: cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c. Parser version: vals-astro-v3. Imported at: 2026-10-15
- Comparison methodology
- Temperature: 1. Top P: 0.95. Maximum output tokens: 30000
Vals Multimodal Index: SWE-bench (Show measurement, test conditions, and source)
- Source value
- 69.608
- Score
- 69.608
- Metric
- benchmark score
- Unit
- %
- Benchmark version
- 1.2
- Category
- aggregate
- Task
- swebench
- Task label
- SWE-bench
- Direction
- Higher is better
- Comparison cohort
- vals-vals-multimodal-index:1.2:swebench
- Source type
- independent-evaluator
- Evaluator
- Vals AI
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Source model ID: minimax/MiniMax-M3. Source model name: MiniMax M3. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-08-11. Latency in seconds: 765.232. Standard error: 4.554. Cost per task in USD: 0.508278. Source ID: vals-ai. Evidence capture ID: vals-vals_multimodal_index-2026-10-15-077b22575f6e. Source payload hash: 077b22575f6e075b7b78157d000ec8f94d7ead409c7dcbcf04887630ed572a2d. Parser version: vals-astro-v3. Imported at: 2026-10-15
Page 1 of 20
Our tests
SVG short test
One SVG prompt and fixed output settings. Captures are shown only with 0 reported reasoning tokens or documented lack of reasoning controls. Identical test conditions do not make the models' internal compute identical.
Earlier tests
Pelican on a bicycle
A community classic for free-form SVG drawing.
MiniMax M3
Reasoning (requested): high
Current attempt
- Run date
- Oct 2, 2026
- API provider
- openrouter
- Requested API model
- minimax/minimax-m3
- API model reported in response
- minimax/minimax-m3
- Reasoning setting
- high
- Pinned endpoint
- CoreWeave | minimax/minimax-m3-20260531
- Temperature
- Provider default
- Token limit including reasoning
- 8,192 tokens
- Test protocol
- community-visual-tests-v1
- Technical checks
- Passed, not a quality rating
- Response time
- 113.2 s
Visually reviewed. This individual test does not establish overall model quality.
Earlier attempts (1)
- Oct 1, 2026API request failedReasoning setting: high
Prompt and test conditions
Generate an SVG of a pelican riding a bicycle
Token limit including reasoning: 8,192 tokens
Task origin (Simon Willison)Popularity
54.6 / 100
Specifications and access
| Specification | Value and source |
|---|---|
| Weights | Open weightsSource |
| Access | API, LocalSource |
| Parameters | 428BSource |
| Active parameters | 23BSource |
| Context window | 1,000,000 tokensSource |
| Notes | Native multimodal model with a 1M context and open weights (Hugging Face, MiniMax community license); about 428B parameters, about 23B active (MoE).Source |
| Release | 2026-06-01 (retrieved 2026-09-24)Source |
| Parameters | 428 B (retrieved 2026-09-24)Source |
| Active parameters | 23 B (retrieved 2026-09-24)Source |
| Context window | 1,048,576 tokens (retrieved 2026-09-24)Source |
| License | MiniMax Community License (retrieved 2026-09-24)Source |
| Input | Text, image, video (retrieved 2026-09-24)Source |
| Reasoning mode | enabled, adaptive, disabled (retrieved 2026-09-24)Source |