MiniMax-M3.1-Flash · Intelligence Index v5.0 ↗
1 more reported result
42.71 index · MiniMax-M3.1-Flash · Intelligence Index v4.3.2 · Artificial Analysis ↗
MiniMax M3.1 Flash
Scores at a glance
37 benchmarks · large dot: MiniMax M3.1 Flash; small dots: closest models where reported
AA-Briefcase v1.1 ↗1473.37 Elo
MiniMax-M3.1-Flash · AA-Briefcase v1.1 · overall Elo ↗
AutomationBench-AA ↗72.52%
MiniMax-M3.1-Flash · AutomationBench-AA · guardrail-gated objective score ↗
GDP.pdf ↗20.80%
MiniMax-M3.1-Flash · GDP.pdf · all-pass ↗
Terminal-Bench 4.0 ↗25.76%
MiniMax-M3.1-Flash · Terminal-Bench 4.0 · AA harness ↗
1 more reported result
25.25 % · MiniMax-M3.1-Flash (Mini-SWE-agent) · Terminal-Bench 4.0 · Score · Vals AI · Terminal-Bench 4.0 ↗
MiniMax-M3.1-Flash · Terminal-Bench-Science 0.1 · AA harness ↗
FrontierCode 2.0 ↗20.82%
MiniMax-M3.1-Flash · FrontierCode 2.0 · AA implementation ↗
MiniMax-M3.1-Flash · CritPt v2 · hard subset · AA implementation ↗
HLE-Diamond ↗28.10%
MiniMax-M3.1-Flash · HLE-Diamond · AA implementation ↗
AA-Omniscience v1.1 ↗-6.40 index
MiniMax-M3.1-Flash · AA-Omniscience v1.1 · error-penalized index ↗
1 more reported result
15.55 index · MiniMax-M3.1-Flash · AA-Omniscience · error-penalized score · Artificial Analysis ↗
MiniMax-M3.1-Flash · AA-Omniscience v1.1 · accuracy ↗
1 more reported result
56.20% · MiniMax-M3.1-Flash · AA-Omniscience · accuracy · Artificial Analysis ↗
MiniMax-M3.1-Flash · AA-Omniscience v1.1 · hallucination rate, lower is better ↗
1 more reported result
92.81% · MiniMax-M3.1-Flash · AA-Omniscience · hallucination rate, lower is better · Artificial Analysis ↗
GDPval-AA v2.1 ↗1457.57 Elo
MiniMax-M3.1-Flash · GDPval-AA v2.1 · Elo ↗
FrontierCode 1.1 ↗38.58%
MiniMax-M3.1-Flash · FrontierCode 1.1 · AA implementation ↗
AA-LCR v1.1 ↗79.67%
MiniMax-M3.1-Flash · AA-LCR v1.1 ↗
SciCode ↗53.36%
MiniMax-M3.1-Flash · SciCode · AA implementation ↗
Humanity’s Last Exam ↗47.96%
MiniMax-M3.1-Flash · Humanity’s Last Exam · AA implementation ↗
MMMU-Pro ↗79.13%
MiniMax-M3.1-Flash · MMMU-Pro · AA implementation ↗
MLCR-AA ↗16.67%
MiniMax-M3.1-Flash · MLCR-AA · overall ↗
CritPt v2 ↗50.57%
MiniMax-M3.1-Flash · CritPt v2 · code tools ↗
CritPt ↗22.29%
MiniMax-M3.1-Flash · CritPt · original ↗
MiniMax M3.1 Flash · BankerToolBench · source score ↗
DeepSWE v1.1 ↗73.7%
MiniMax M3.1 Flash · DeepSWE v1.1 ↗
OSWorld 2.0 ↗61.7
MiniMax M3.1 Flash · OSWorld V2 · headline points ↗
MiniMax M3.1 Flash · Agents’ Last Exam · headline points ↗
CyberGym ↗82.0%
MiniMax M3.1 Flash · CyberGym ↗
ErdősBench ↗3.010 / 4
MiniMax M3.1 Flash · ErdősBench · mean progress / 4 · API ↗
Vals Index ↗53.78 %
MiniMax-M3.1-Flash · Vals Index · Accuracy ↗
Vals Finance Index ↗55.91 %
MiniMax-M3.1-Flash · Vals Finance Index · Accuracy ↗
Vals Legal Index ↗67.07 %
MiniMax-M3.1-Flash · Vals Legal Index · Accuracy ↗
Legal Research Bench ↗34.13 %
MiniMax-M3.1-Flash · Legal Research Bench · All-Pass ↗
HLAB-Vals-1.1 ↗7.5 %
MiniMax-M3.1-Flash · HLAB-Vals-1.1 · Task Pass Rate ↗
Vals Finance Agent v2.1 ↗58.83 %
MiniMax-M3.1-Flash · Finance Agent · Accuracy ↗
MiniMax-M3.1-Flash · Excel Modeling Benchmark · Accuracy ↗
Tax Agent Bench ↗32.14 %
MiniMax-M3.1-Flash · Tax Agent Bench · Accuracy ↗
Vibe Code Bench ↗73.94 %
MiniMax-M3.1-Flash (OpenHands) · Vibe Code Bench · original task set ↗
GDPx v1.0 ↗4.0%
MiniMax M3.1 Flash · GDPx v1.0 · Overall · intended grading ↗
53 more reported results
3.6% · MiniMax M3.1 Flash · GDPx v1.0 · Eight-domain subset · intended grading · GDPx v1.0 — SemiAnalysis ↗
6.6% · MiniMax M3.1 Flash · GDPx v1.0 · Recursive Self-Improvement · intended grading · GDPx v1.0 — SemiAnalysis ↗
0.1% · MiniMax M3.1 Flash · GDPx v1.0 · Chip Design · intended grading · GDPx v1.0 — SemiAnalysis ↗
7.4% · MiniMax M3.1 Flash · GDPx v1.0 · Cybersecurity · intended grading · GDPx v1.0 — SemiAnalysis ↗
7.7% · MiniMax M3.1 Flash · GDPx v1.0 · Biology · intended grading · GDPx v1.0 — SemiAnalysis ↗
0.0% · MiniMax M3.1 Flash · GDPx v1.0 · Finance · intended grading · GDPx v1.0 — SemiAnalysis ↗
0.0% · MiniMax M3.1 Flash · GDPx v1.0 · Legal · intended grading · GDPx v1.0 — SemiAnalysis ↗
15.5% · MiniMax M3.1 Flash · GDPx v1.0 · Quant Trading · intended grading · GDPx v1.0 — SemiAnalysis ↗
2.2% · MiniMax M3.1 Flash · GDPx v1.0 · Hardware Design · intended grading · GDPx v1.0 — SemiAnalysis ↗
2.3% · MiniMax M3.1 Flash · GDPx v1.0 · Materials Science · intended grading · GDPx v1.0 — SemiAnalysis ↗
0.0% · MiniMax M3.1 Flash · GDPx v1.0 · Alignment · intended grading · GDPx v1.0 — SemiAnalysis ↗
2.2% · MiniMax M3.1 Flash · GDPx v1.0 · Software Engineering · intended grading · GDPx v1.0 — SemiAnalysis ↗
0.0% · MiniMax M3.1 Flash · GDPx v1.0 · Aria · Chip Design · intended grading · GDPx v1.0 — SemiAnalysis ↗
0.0% · MiniMax M3.1 Flash · GDPx v1.0 · Arcverex · Chip Design · intended grading · GDPx v1.0 — SemiAnalysis ↗
0.3% · MiniMax M3.1 Flash · GDPx v1.0 · Ergodex · Chip Design · intended grading · GDPx v1.0 — SemiAnalysis ↗
7.4% · MiniMax M3.1 Flash · GDPx v1.0 · Arithmetic · Cybersecurity · intended grading · GDPx v1.0 — SemiAnalysis ↗
7.7% · MiniMax M3.1 Flash · GDPx v1.0 · LatchBio · Biology · intended grading · GDPx v1.0 — SemiAnalysis ↗
0.0% · MiniMax M3.1 Flash · GDPx v1.0 · Living Context · Finance · intended grading · GDPx v1.0 — SemiAnalysis ↗
0.0% · MiniMax M3.1 Flash · GDPx v1.0 · Chakra · Legal · intended grading · GDPx v1.0 — SemiAnalysis ↗
15.5% · MiniMax M3.1 Flash · GDPx v1.0 · Third Moment · Quant Trading · intended grading · GDPx v1.0 — SemiAnalysis ↗
6.6% · MiniMax M3.1 Flash · GDPx v1.0 · Extrapolate · Recursive Self-Improvement · intended grading · GDPx v1.0 — SemiAnalysis ↗
2.2% · MiniMax M3.1 Flash · GDPx v1.0 · Beautiful Machines · Hardware Design · intended grading · GDPx v1.0 — SemiAnalysis ↗
0.6% · MiniMax M3.1 Flash · GDPx v1.0 · ValenceForge · Materials Science · intended grading · GDPx v1.0 — SemiAnalysis ↗
3.9% · MiniMax M3.1 Flash · GDPx v1.0 · Emulated · Materials Science · intended grading · GDPx v1.0 — SemiAnalysis ↗
0.0% · MiniMax M3.1 Flash · GDPx v1.0 · Fleet · Alignment · intended grading · GDPx v1.0 — SemiAnalysis ↗
2.2% · MiniMax M3.1 Flash · GDPx v1.0 · Datacurve · Software Engineering · intended grading · GDPx v1.0 — SemiAnalysis ↗
8.2% · MiniMax M3.1 Flash · GDPx v1.0 · Overall · partial credit · GDPx v1.0 — SemiAnalysis ↗
8.4% · MiniMax M3.1 Flash · GDPx v1.0 · Eight-domain subset · partial credit · GDPx v1.0 — SemiAnalysis ↗
6.6% · MiniMax M3.1 Flash · GDPx v1.0 · Recursive Self-Improvement · partial credit · GDPx v1.0 — SemiAnalysis ↗
0.2% · MiniMax M3.1 Flash · GDPx v1.0 · Chip Design · partial credit · GDPx v1.0 — SemiAnalysis ↗
7.4% · MiniMax M3.1 Flash · GDPx v1.0 · Cybersecurity · partial credit · GDPx v1.0 — SemiAnalysis ↗
16.2% · MiniMax M3.1 Flash · GDPx v1.0 · Biology · partial credit · GDPx v1.0 — SemiAnalysis ↗
22.2% · MiniMax M3.1 Flash · GDPx v1.0 · Finance · partial credit · GDPx v1.0 — SemiAnalysis ↗
14.2% · MiniMax M3.1 Flash · GDPx v1.0 · Legal · partial credit · GDPx v1.0 — SemiAnalysis ↗
15.5% · MiniMax M3.1 Flash · GDPx v1.0 · Quant Trading · partial credit · GDPx v1.0 — SemiAnalysis ↗
2.2% · MiniMax M3.1 Flash · GDPx v1.0 · Hardware Design · partial credit · GDPx v1.0 — SemiAnalysis ↗
3.8% · MiniMax M3.1 Flash · GDPx v1.0 · Materials Science · partial credit · GDPx v1.0 — SemiAnalysis ↗
0.0% · MiniMax M3.1 Flash · GDPx v1.0 · Alignment · partial credit · GDPx v1.0 — SemiAnalysis ↗
2.2% · MiniMax M3.1 Flash · GDPx v1.0 · Software Engineering · partial credit · GDPx v1.0 — SemiAnalysis ↗
0.3% · MiniMax M3.1 Flash · GDPx v1.0 · Aria · Chip Design · partial credit · GDPx v1.0 — SemiAnalysis ↗
0.0% · MiniMax M3.1 Flash · GDPx v1.0 · Arcverex · Chip Design · partial credit · GDPx v1.0 — SemiAnalysis ↗
0.3% · MiniMax M3.1 Flash · GDPx v1.0 · Ergodex · Chip Design · partial credit · GDPx v1.0 — SemiAnalysis ↗
7.4% · MiniMax M3.1 Flash · GDPx v1.0 · Arithmetic · Cybersecurity · partial credit · GDPx v1.0 — SemiAnalysis ↗
16.2% · MiniMax M3.1 Flash · GDPx v1.0 · LatchBio · Biology · partial credit · GDPx v1.0 — SemiAnalysis ↗
22.2% · MiniMax M3.1 Flash · GDPx v1.0 · Living Context · Finance · partial credit · GDPx v1.0 — SemiAnalysis ↗
14.2% · MiniMax M3.1 Flash · GDPx v1.0 · Chakra · Legal · partial credit · GDPx v1.0 — SemiAnalysis ↗
15.5% · MiniMax M3.1 Flash · GDPx v1.0 · Third Moment · Quant Trading · partial credit · GDPx v1.0 — SemiAnalysis ↗
6.6% · MiniMax M3.1 Flash · GDPx v1.0 · Extrapolate · Recursive Self-Improvement · partial credit · GDPx v1.0 — SemiAnalysis ↗
2.2% · MiniMax M3.1 Flash · GDPx v1.0 · Beautiful Machines · Hardware Design · partial credit · GDPx v1.0 — SemiAnalysis ↗
1.6% · MiniMax M3.1 Flash · GDPx v1.0 · ValenceForge · Materials Science · partial credit · GDPx v1.0 — SemiAnalysis ↗
6.0% · MiniMax M3.1 Flash · GDPx v1.0 · Emulated · Materials Science · partial credit · GDPx v1.0 — SemiAnalysis ↗
0.0% · MiniMax M3.1 Flash · GDPx v1.0 · Fleet · Alignment · partial credit · GDPx v1.0 — SemiAnalysis ↗
2.2% · MiniMax M3.1 Flash · GDPx v1.0 · Datacurve · Software Engineering · partial credit · GDPx v1.0 — SemiAnalysis ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
GPT-6 Luna →OpenAI
29 of 30 shared benchmark comparisons
Step 5 Preview →StepFun
25 of 30 shared benchmark comparisons
Mistral Large 4 Preview →Mistral
19 of 30 shared benchmark comparisons
How similarity is measured
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
About the model report
The public launch highlights agentic work, coding, computer use, and security. Reported task cost and headline quality remain separate measurements. Reviewed 2026-10-25.
Read the official model report ↗6 benchmarks in the report
Search this collection →AutomationBench-AA
Agents orchestrate workflows in simulated SaaS systems while respecting operational constraints.
Objectives completed↗
DeepSWE v1.1
Original engineering problems test coding agents on substantial changes in existing repositories.
Verified task success↗
Agents’ Last Exam
Professional software workflows test whether an agent can deliver the requested result in a real application environment.
Professional task success↗
OSWorld 2.0
Long-horizon computer workflows extend evaluation across applications, files, and realistic task sequences.
Partial and binary task score↗
BankerToolBench
Financial work tests sustained planning, consistency across documents, compliance constraints, and linked tool actions.
Financial workflow score↗
CyberGym
A controlled security benchmark appears in MiniMax’s recent model capability report.
Controlled security task success↗
COMPARISON CHECKLIST
Match benchmark version, task subset, model effort, harness, tool access, attempt budget, scoring rule, and fallback behavior. A shared benchmark name is the start of a comparison, not proof that two reported scores use the same contract.
MiniMax original report ↗