Gemini 3.7 Flash vs Minimax M2 5
As of Oct 14, 2026, Gemini 3.7 Flash leads Minimax M2 5 in 6 of 6 shared categories: General LLM, Reasoning, Coding › Web dev, Long context, Factuality, and Abstraction (ARC).
Gemini 3.7 Flash
Yes. Yes on Vision (best per dollar). Not the overall leader.
Minimax M2 5
It used to be. Was SOTA in Coding › Web dev.
| Category | Gemini 3.7 Flash | Minimax M2 5 |
|---|---|---|
| General LLM | #14 · #14 in General LLM Margin 9.523809523809518 LMArena leaderboard dataset · Oct 13, 2026 | #127 · #127 in General LLM Margin 86.39455782312925 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #16 · #16 in Reasoning Margin 11.643835616438352 LMArena leaderboard dataset · Oct 13, 2026 | #119 · #119 in Reasoning Margin 82.1917808219178 LMArena leaderboard dataset · Oct 13, 2026 |
| Math | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 |
| Science | #5 · #5 in Science Margin — Epoch AI benchmarking hub · Aug 13, 2026 | — |
| Coding | #20 · #20 in Coding Margin 100 Terminal-Bench Harbor Hub · Oct 6, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 |
| Coding › Agentic | #20 · #20 in Coding › Agentic Margin 100 Terminal-Bench Harbor Hub · Oct 6, 2026 | — |
| Coding › Web dev | #25 · #25 in Coding › Web dev Margin 22.429906542056074 LMArena leaderboard dataset · Oct 13, 2026 | #77 · #77 in Coding › Web dev Margin 71.02803738317758 LMArena leaderboard dataset · Oct 13, 2026 |
| Long context | #14 · #14 in Long context Margin 9.523809523809518 LMArena leaderboard dataset · Oct 13, 2026 | #116 · #116 in Long context Margin 78.91156462585033 LMArena leaderboard dataset · Oct 13, 2026 |
| Vision | #14 · #14 in Vision Margin 39.473684210526315 Epoch AI benchmarking hub · Aug 13, 2026 | — |
| Factuality | #15 · Was SOTA · Factuality Margin 11.940298507462686 LMArena leaderboard dataset · Oct 13, 2026 | #113 · #113 in Factuality Margin 85.07462686567165 LMArena leaderboard dataset · Oct 13, 2026 |
| Abstraction (ARC) | #6 · #6 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Aug 13, 2026 | #36 · #36 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Feb 12, 2026 |
Gemini 3.7 Flash: $1.5 per 1M blended tokens.
Minimax M2 5: $0.47250000000000003 per 1M blended tokens.
Gemini 3.7 Flash: closed weights.
Minimax M2 5: open weights.
General LLM: As of Oct 14, 2026, Gemini 3.7 Flash leads Minimax M2 5 in General LLM at #14 against #127.
Reasoning: As of Oct 14, 2026, Gemini 3.7 Flash leads Minimax M2 5 in Reasoning at #16 against #119.
Coding › Web dev: As of Oct 14, 2026, Gemini 3.7 Flash leads Minimax M2 5 in Coding › Web dev at #25 against #77.
Long context: As of Oct 14, 2026, Gemini 3.7 Flash leads Minimax M2 5 in Long context at #14 against #116.
Factuality: As of Oct 14, 2026, Gemini 3.7 Flash leads Minimax M2 5 in Factuality at #15 against #113.
Abstraction (ARC): As of Oct 14, 2026, Gemini 3.7 Flash leads Minimax M2 5 in Abstraction (ARC) at #6 against #36.
Gemini 3.7 Flash · Minimax M2 5
Gemini 3.7 Flash or Minimax M2 5?
As of Oct 14, 2026, Gemini 3.7 Flash leads Minimax M2 5 in 6 of 6 shared categories: General LLM, Reasoning, Coding › Web dev, Long context, Factuality, and Abstraction (ARC).
Gemini 3.7 Flash or Minimax M2 5 for General LLM?
As of Oct 14, 2026, Gemini 3.7 Flash leads Minimax M2 5 in General LLM at #14 against #127.
Gemini 3.7 Flash or Minimax M2 5 for Reasoning?
As of Oct 14, 2026, Gemini 3.7 Flash leads Minimax M2 5 in Reasoning at #16 against #119.
Gemini 3.7 Flash or Minimax M2 5 for Coding › Web dev?
As of Oct 14, 2026, Gemini 3.7 Flash leads Minimax M2 5 in Coding › Web dev at #25 against #77.