Atlas

Compare Models

Claude Fable 5.1 vs MiniMax M3.1 Flash

Claude Fable 5.1 leads by 5.9 capability points (≈95% interval +3.3 to +8.4): a clear lead over MiniMax M3.1 Flash · P(higher) ≈ 100%

Wins 26 of 27 shared benchmarks (1 lost)

Capability vs. relative cost
Claude Fable 5.1MiniMax M3.1 FlashClosed weightsOpen weights

Each line runs through one model’s priced reasoning settings, cheapest to most expensive; grey points are other models’ priced settings in the same range. Results whose reasoning effort the source didn’t report are left out wherever a model has named effort levels. Capability and relative cost are the published estimates (relative cost is cost per task as a multiple of GPT-5 (high)); hover a setting, or use the arrow keys, to set it beside the other model’s same setting.

Claude Fable 5.1vsMiniMax M3.1 Flashcapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins26 – 1 · 27 shared

Comparing matching setups only (40 benchmarks excluded) · suites counted once
← Claude Fable 5.1MiniMax M3.1 Flash →

Claude Fable 5.1vsMiniMax M3.1 Flashwins by categoryData Nov 15, 2026Data: Mercor, Scale AI, Artificial Analysis and 15 othersVillage LLM Atlasatlas.village.dev

Margins

Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is MiniMax M3.1 Flash minus Claude Fable 5.1.

Toloka Arena (v3)Agents71.022.0−49.0
ALE-BenchCode28491495−48.0
NoCoT-Bench NCKI (kspine v3)General QA12865.9−43.2
Visa Agentic Commerce BenchmarkAgents75.633.3−42.2
TaxCalcBench TY25Finance & Accounting42.00.0−42.0
NoCoT-Bench NCRI 15.2General QA12868.4−32.8
GBENCH One-shot Coding GScoreGames69.341.1−28.2
BuseyBench SVGMultimodal7.04.2−28.1
DAXBench v2Code91.563.8−27.7
Humanity's Last Exam DiamondGeneral QA51.328.1−23.2
Artificial Analysis Intelligence Index v5.0Indexes49.028.9−20.1
FrontierML ($200 wallet)Agents41.923.2−18.7
τ³-Banking (Mercor run, bm25_grep retrieval)Agents54.036.1−17.9
Tax Agent BenchFinance & Accounting77.962.7−15.2
LiveBench 2.0Agents88.073.1−14.9
GDPval-AA v2.1Professional Work17351465−11.9
APEX-Agents 1.1Professional Work77.168.1−9.0
Excel Modeling Benchmark v1.1Finance & Accounting76.767.8−8.9
APEX-1 (Mercor, mean score)Professional Work73.865.0−8.8
APEX-Accounting 1.1Finance & Accounting66.760.0−6.7
Professional Reasoning Benchmark - LegalLegal51.645.1−6.5
Design Arena Overall Code CategoriesCode13311297−5.6
Harvey LAB (Mercor run, undisclosed ~213-task cohort)Legal17.411.9−5.5
Professional Reasoning Benchmark - FinanceFinance & Accounting50.845.6−5.1
GDPxProfessional Work8.54.0−4.5
HiL-Bench (Human-in-Loop Benchmark)Agents61.565.7+4.2
PostTrainBench Average (v1.1)Indexes40.239.3−0.9

Claude Fable 5.1vsMiniMax M3.1 Flashnormalised score marginsData Nov 15, 2026Data: Mercor, Scale AI, Artificial Analysis and 15 othersVillage LLM Atlasatlas.village.dev

Win counts use each benchmark’s declared score direction. Represented suite slices and the derived Capability score are excluded from headline totals. Missing or incompatible setups are excluded, never counted as losses.
Loading Atlas data…