Atlas

Compare Models

Grok 4.7 vs MiniMax M3.1 Flash

Grok 4.7 leads by 0.8 capability points (≈95% interval −1.6 to +3.1): statistically tied · P(higher) ≈ 73%

Wins 27 of 33 shared benchmarks (6 lost)

Capability vs. relative cost
Grok 4.7MiniMax 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.

Grok 4.7vsMiniMax M3.1 Flashcapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins27 – 6 · 33 shared

Comparing matching setups only (57 benchmarks excluded) · suites counted once
← Grok 4.7MiniMax M3.1 Flash →

Grok 4.7vsMiniMax M3.1 Flashwins by categoryData Nov 15, 2026Data: Vals AI, Mercor, Bake AI 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 Grok 4.7.

DAXBench v2Code92.663.8−28.7
FoodTruck BenchGames4256163464+26.8
Visa Agentic Commerce BenchmarkAgents60.033.3−26.7
RSI Arena Stage 1 human ratingAgents10381002−17.3
GBENCH One-shot Coding GScoreGames56.341.1−15.1
Legal Research BenchLegal47.134.1−13.0
o11y-bench 1.1 Pass^3Agents76.664.1−12.5
FrontierML ($200 wallet)Agents10.923.2+12.3
Vibe Code Bench v1.1Code86.273.9−12.2
ALE-BenchCode18231495−11.6
HLAB-Vals-1.1Legal18.37.5−10.8
Toloka Arena (v3)Agents31.022.0−9.0
TaxCalcBench TY25Finance & Accounting8.00.0−8.0
Harvey LAB (Mercor run, undisclosed ~213-task cohort)Legal19.511.9−7.6
Tax Agent BenchFinance & Accounting69.062.7−6.3
Vals Legal IndexIndexes72.767.1−5.6
Vals Index v2.2Indexes58.653.8−4.8
APEX-Accounting 1.1Finance & Accounting55.360.0+4.7
Design Arena Overall Code CategoriesCode12701297+4.5
Excel Modeling Benchmark v1.1Finance & Accounting71.567.8−3.7
Code Migration v1.1 (Vals Index v2.2 subset)Code51.848.2−3.6
Terminal-Bench 4.0Code28.825.3−3.5
BuseyBench SVGMultimodal4.64.2−3.5
τ³-Banking (Mercor run, bm25_grep retrieval)Agents32.636.1+3.5
SAGE v1.1Math88.785.3−3.4
Vals Finance IndexIndexes58.855.9−2.9
DeepSWE v1.1Code71.068.1−2.9
Finance Agent v2.1Finance & Accounting60.658.8−1.8
LiveBench 2.0Agents74.173.1−1.0
APEX-Agents 1.1Professional Work68.768.1−0.6
APEX-1 (Mercor, mean score)Professional Work65.465.0−0.4
Access to Justice BenchmarkLegal73.773.3−0.4
GDPxProfessional Work3.94.0+0.1

Grok 4.7vsMiniMax M3.1 Flashnormalised score marginsData Nov 15, 2026Data: Vals AI, Mercor, Bake AI 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…