RankingEffort benchmarks

MiniMax-M2.7 · Reasoning effort benchmarks

Compare measured Low, Medium, High and other settings. Every number keeps its source.

Model

MiniMax-M2.7

29 measured results · 2 reported effort labels · 29 benchmark/harness combinations. Model evidence and sources →

Capability score evidence

MiniMax-M2.7 · Reasoning: 15.9 overall comparison score. Meets the overall evidence requirements.

Which sources carry the weight?

Artificial Analysis · 100.0% direct comparison weight · independent

These shares describe the comparisons entering the fit, not fractions of the final score.

How sensitive is this score?

Remove one evaluator or family and refit the graph against the same overall panel. Values use the matching dataset audited 2026-09-12. These are sensitivity checks, not confidence intervals; ranking eligibility may also change.

Removed evidence	Recomputed score	Change
Artificial Analysis	Comparison path lost	—
ARC Prize	18.3	+2.4
Datacurve	13.7	-2.1
LiveCodeBench	15.7	-0.1
Scale	17.1	+1.3
Terminal-Bench	15.9	+0.0
Cognition	16.4	+0.5
LiveBench	16.1	+0.2
SWE-rebench	16.2	+0.4
Epoch AI	16.0	+0.2
Vals AI	15.4	-0.5
Provider reports · Anthropic	15.9	+0.0
Provider reports · Moonshot AI	15.8	-0.0
Provider reports · Meta	15.8	-0.0
Provider reports · Mistral	15.9	+0.0
All provider reports	15.8	-0.0

Every benchmark family

Removed evidence	Recomputed score	Change
arc-agi	18.2	+2.3
deepswe	13.8	-2.1
ifbench	14.8	-1.1
apex-agents	16.6	+0.8
gpqa	15.1	-0.8
mmmu-pro	16.6	+0.7
itbench	16.4	+0.6
epoch-game-puzzles	15.3	-0.6
scicode	15.3	-0.5
frontiercode	16.4	+0.5
simpleqa	16.4	+0.5
automationbench	16.3	+0.4
critpt	16.3	+0.4
swe-rebench	16.2	+0.4
gdp-pdf	16.2	+0.3
mmlu-pro	16.2	+0.3
gdpval	15.6	-0.3
aa-lcr	15.6	-0.2
tau-bench	16.1	+0.2
harvey	15.6	-0.2
multi-swe-bench	15.6	-0.2
livebench-instructions	16.0	+0.2
terminal-bench	16.0	+0.2
analyst-agent	16.0	+0.2
livebench-language	16.0	+0.2
swe-atlas-qna	15.7	-0.1
frontiermath	16.0	+0.1
arc-agi-3	15.8	-0.1
livebench-coding	15.8	-0.1
vibe-code	15.8	-0.1
briefcase	15.9	+0.1
livebench-reasoning	15.8	-0.1
hle	15.9	+0.1
vals-finance-agent	15.8	-0.1
swe-atlas-test-writing	15.8	-0.1
vals-legal-research	15.8	-0.1
enterprise-ops	15.8	-0.1
livecodebench	15.8	-0.0
vals-code-migration	15.8	-0.0
gmmlu	15.9	+0.0
math500	15.9	+0.0
swe-atlas-refactoring	15.8	-0.0
livebench-data	15.9	+0.0
livebench-math	15.9	+0.0
omniscience	15.8	-0.0
vals-excel-modeling	15.8	-0.0
aime	15.9	+0.0
enigma-eval	15.9	+0.0
swe-bench-pro	15.9	+0.0

What evidence is missing from the fit?

Across all collected settings for this model: 84 observations, 20 contributing, 0 matched without graph weight and 64 excluded. Counts do not establish rank eligibility.

1 · Benchmark family or source protocol has not been reviewed
8 · Effort is not identified
23 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately
32 · Supporting evidence outside the reviewed capability core

Inspect every observation and exclusion →

Capability profile

One configuration, seven capabilities

Comparison score · 0–100

AMiniMax-M2.7 · Reasoning4 of 7 capabilities supported

Gaps are unknown, not zero. Hollow points are preliminary.

Agentic
A15.0Supported
Hard reasoning
A22.1Supported
Coding
A22.8Supported
Human pref
Unknown
Knowledge
A26.6Supported
Multimodal
Unknown
Long context
A23.9Preliminary

Each profile belongs to the named configuration. Capability scores use a shared panel for all axes, distinct from the overall ranking panel; they are not accuracy percentages or direct head-to-head wins.

Compare this configuration →Explore the model evidence profile →

These are published benchmark scores. Supported effort estimates also appear on the Capability leaderboard. Results from different harnesses occupy different rows. Missing cells stay unknown; no scores are copied between effort levels.

Benchmark / source	Reasoning	Unspecified
AA-AnalystAgentArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of tasks solved on all 5 of 5 attempts · 80 tasks, 5 attempts per task · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	11.25% Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
AA-Briefcase EloArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Briefcase is an agentic knowledge work benchmark developed by Artificial Analysis. AA-Briefcase Elo is a combined metric that aggregates rubric pass rate, analytical quality Elo and presentation Elo · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-09-12.	715.25 Elo Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
APEX-Agents-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	10.62% Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
AA-LCR v1.1Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	78.33% Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
AutomationBench-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of task objectives completed with no guardrail violations · Higher is better · Benchmark developed by Zapier · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	4.44% Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
CritPtArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by Argonne and UIUC, with contributions from 60+ researchers globally · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	0.57% Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
GDP.pdf: All-passArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of attempts where every atomic criterion passed · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	6% Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
GDPval-AA v2 LeaderboardArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Elo rating for performance on real-world work tasks · Anchored to a human baseline of 1,000 · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-09-12.	1,087.02 Elo Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
GPQA DiamondArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	87.37% Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
Humanity's Last ExamArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	29.61% Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
IFBenchArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	75.71% Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
ITBench-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Combined public and private Site Reliability Engineering (SRE) tasks · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	26.46% Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
MLCR-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of tasks judged accurate, complete, and concise · Expert + compound (hard) sets · Benchmark developed by Wisedocs · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	3.33% Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
AA-Omniscience IndexArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis Unit: index. Source collected 2026-09-12.	0.77 Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
AA-Omniscience AccuracyArtificial Analysis · 6000 questions; 1 attempt; correct-answer share; GPT-5.6 Luna medium grader Benchmark details AA-Omniscience Accuracy (higher is better) measures the proportion of correctly answered questions out of all questions, regardless of whether the model chooses to answer · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	26.8% Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
SciCodeArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	50.12% Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
𝜏²-Bench TelecomArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	84.8% Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
𝜏³-BankingArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by Sierra Research · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	9.9% Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
Terminal-Bench HardArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	39.39% Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
Terminal-Bench v2.1Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by the Laude Institute and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	55.43% Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
Terminal-Bench v4.0Artificial Analysis · mini-SWE-agent v2.4.6; 66 tasks; pass@1 averaged over 3 repeats; 500 steps; task timeout up to 8 hours Benchmark details Benchmark developed by the Laude Institute, Stanford, and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	0% Reported settings MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
Vals AI · Finance Agent v2Vals AI · Vals FAB v2 shared six-tool harness; two-hour task limit Benchmark details Overall weighted rubric accuracy, averaged over three runs on 450 tasks. Dealbreaker failures and timeouts score zero. Related categories and all-pass scores are not additional votes. Three-model judge panel; private test set. Unit: percent. Source collected 2026-09-12.	Not reported	27.89% Reported settings {"checkpoint":"MiniMax-M2.7","evaluatorModel":"minimax/MiniMax-M2.7","sourceUpdatedOn":"2026-09-10","reasoning_effort":null,"compute_effort":null,"reasoning":null,"temperature":1,"top_p":0.95,"max_output_tokens":196608,"verbosity":null,"provider":"MiniMax","harness":null}
Vals AI · Code Migration v1Vals AI · Vals Code Migration shared agent harness Benchmark details Hidden behavior-test pass rate, equally weighted across 40 repositories (30 CLI and 10 COBOL-to-Java). Anti-cheat failures score zero. Code-quality ratings and language splits are not additional votes. Unit: percent. Source collected 2026-09-12.	Not reported	8.69% Reported settings {"checkpoint":"MiniMax-M2.7","evaluatorModel":"minimax/MiniMax-M2.7","sourceUpdatedOn":"2026-09-10","reasoning_effort":null,"compute_effort":null,"reasoning":null,"temperature":1,"top_p":0.95,"max_output_tokens":80000,"verbosity":null,"provider":"MiniMax","harness":null}
Vals AI · Legal Research Bench v1Vals AI · Vals Legal Research shared five-tool harness; three-hour task limit Benchmark details All-pass accuracy on 208 private legal research tasks. Every expert rubric check must pass; GPT-5.4 judges responses. Partial-credit scores and practice-area splits are not additional votes. Unit: percent. Source collected 2026-09-12.	Not reported	10.58% Reported settings {"checkpoint":"MiniMax-M2.7","evaluatorModel":"minimax/MiniMax-M2.7","sourceUpdatedOn":"2026-09-10","reasoning_effort":null,"compute_effort":null,"reasoning":null,"temperature":1,"top_p":0.95,"max_output_tokens":80000,"verbosity":null,"provider":"MiniMax","harness":null}
Vals AI · Excel Modeling Benchmark v1Vals AI · Vals EMB shared workbook agent harness; 3.5-hour task limit Benchmark details Mean of seven equally weighted task categories. Template submissions use recalculated Excel cell accuracy; scratch submissions use rubric checks judged by GPT-5.4 Mini XHigh. Partial credit does not mean task completion. Unit: percent. Source collected 2026-09-12.	Not reported	28.45% Reported settings {"checkpoint":"MiniMax-M2.7","evaluatorModel":"minimax/MiniMax-M2.7","sourceUpdatedOn":"2026-09-10","reasoning_effort":null,"compute_effort":null,"reasoning":null,"temperature":1,"top_p":0.95,"max_output_tokens":80000,"verbosity":null,"provider":"MiniMax","harness":null}
Vals AI · MMLU-Pro v1Vals AI · Vals MMLU-Pro five-shot chain-of-thought; regex answer grading Benchmark details Mean accuracy across 14 subjects under Vals five-shot prompting. Subject splits share one family and are not additional votes. Vals labels this benchmark archived; it is historical corroboration, not ongoing frontier evaluation. Unit: percent. Source collected 2026-09-12.	Not reported	80.43% Reported settings {"checkpoint":"MiniMax-M2.7","evaluatorModel":"minimax/MiniMax-M2.7","sourceUpdatedOn":"2026-09-01","reasoning_effort":null,"compute_effort":null,"reasoning":null,"temperature":1,"top_p":0.95,"max_output_tokens":80000,"verbosity":null,"provider":"MiniMax","harness":null}
Vals AI · Terminal-Bench 2.1Vals AI · Vals Terminus 2 harness; pass@1 on 89 tasks Benchmark details Overall task pass rate under the shared Terminus 2 configuration. All task tests must pass. Difficulty splits share one family. Fable 5 and Opus 5 mixed-checkpoint fallback runs are excluded. Unit: percent. Source collected 2026-09-12.	Not reported	48.69% Reported settings {"checkpoint":"MiniMax-M2.7","evaluatorModel":"minimax/MiniMax-M2.7","sourceUpdatedOn":"2026-09-10","reasoning_effort":null,"compute_effort":null,"reasoning":null,"temperature":1,"top_p":0.95,"max_output_tokens":196608,"verbosity":null,"provider":"MiniMax","harness":null}
Vals AI · Vibe Code Bench v1.1Vals AI · Vals modified OpenHands harness; five hours or 1,000 turns per app Benchmark details Mean app test pass rate on the canonical v1.1 test set. Browser Use executes workflow tests; each test requires at least 90% of its substeps. Automated judging can introduce error. Alternate agents are excluded. Unit: percent. Source collected 2026-09-12.	Not reported	11.93% Reported settings {"checkpoint":"MiniMax-M2.7","evaluatorModel":"minimax/MiniMax-M2.7","sourceUpdatedOn":"2026-09-10","reasoning_effort":null,"compute_effort":null,"reasoning":null,"temperature":1,"top_p":0.95,"max_output_tokens":196608,"verbosity":null,"provider":"MiniMax","harness":"OpenHands"}
Vals AI · Harvey Legal Agent Benchmark v1Vals AI · Vals Harvey held-out legal file-work protocol; internet disabled Benchmark details Mean task resolution across two judges (GPT-5.5 Medium and Sonnet 4.6), requiring every criterion to pass. Criteria pass rates and practice-area splits do not add votes. Shared Harvey family; Fable 5 fallback run excluded. Unit: percent. Source collected 2026-09-12.	Not reported	0% Reported settings {"checkpoint":"MiniMax-M2.7","evaluatorModel":"minimax/MiniMax-M2.7","sourceUpdatedOn":"2026-09-10","reasoning_effort":null,"compute_effort":null,"reasoning":null,"temperature":1,"top_p":0.95,"max_output_tokens":80000,"verbosity":null,"provider":"MiniMax","harness":null}

What these comparisons mean

Each source reports its own effort labels. Matching labels do not establish equal compute budgets or identical fallback behavior. Open Reported settings to inspect the exact model name, agent and task coverage. Multiple results at one level remain visible rather than selecting the best. Source-reported None or Non-reasoning labels are not treated as evidence that an API supports those settings.

These measurements use their own dated source collection. The leaderboard fits identified configurations jointly; it contains no pooled model ratings. Explicit thinking budgets are separate configurations. Read the methodology.

Download all effort benchmark results · 7,424 results across 240 models · Collected 2026-09-12

MiniMax-M2.7 · Reasoning effort benchmarks

MiniMax-M2.7

Capability score evidence

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context