Atlas

Compare Models

Grok 4.6 vs MiniMax M3.1 Flash

Grok 4.6 leads by 0.2 capability points (≈95% interval −2.2 to +2.5): statistically tied · P(higher) ≈ 55%

Wins 15 of 22 shared benchmarks (7 lost)

Capability vs. relative cost
Grok 4.6MiniMax 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 4.6vsMiniMax M3.1 Flashcapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins15 – 7 · 22 shared

Comparing matching setups only (49 benchmarks excluded) · suites counted once
← Grok 4.6MiniMax M3.1 Flash →

Grok 4.6vsMiniMax M3.1 Flashwins by categoryData Nov 15, 2026Data: Vals AI, Mercor, Neel Nanda and 13 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 4.6.

Toloka Arena (v3)Agents56.022.0−34.0
NoCoT-Bench NCKI (kspine v3)General QA11265.9−31.7
DAXBench v2Code86.263.8−22.3
GBENCH One-shot Coding GScoreGames55.441.1−14.2
Legal Research BenchLegal48.134.1−13.9
ALE-BenchCode18221495−11.6
NoCoT-Bench NCRI 15.2General QA86.868.4−10.1
τ³-Banking (Mercor run, bm25_grep retrieval)Agents45.736.1−9.6
APEX-Agents 1.1Professional Work77.368.1−9.2
Tax Agent BenchFinance & Accounting71.462.7−8.7
Humanity's Last Exam DiamondGeneral QA19.628.1+8.5
Terminal-Bench 4.0Code17.225.3+8.1
FoodTruck BenchGames5953763464+5.0
BuseyBench SVGMultimodal4.64.2−3.9
DeepSWE v1.1Code65.268.1+2.9
APEX-1 (Mercor, mean score)Professional Work67.765.0−2.7
CyberGymCybersecurity79.782.2+2.5
Vibe Code Bench v1.1Code76.273.9−2.3
Access to Justice BenchmarkLegal71.373.3+2.0
LiveBench 2.0Agents74.973.1−1.8
Design Arena Overall Code CategoriesCode12881297+1.5
APEX-Accounting 1.1Finance & Accounting60.360.0−0.3

Grok 4.6vsMiniMax M3.1 Flashnormalised score marginsData Nov 15, 2026Data: Vals AI, Mercor, Neel Nanda and 13 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…