Gemini 2.5 Pro vs Gemini 3.1 Pro Preview
As of Oct 15, 2026, Gemini 2.5 Pro leads Gemini 3.1 Pro Preview in 0 of 7 shared categories.
Gemini 2.5 Pro
It used to be. Was SOTA in General LLM.
Gemini 3.1 Pro Preview
Yes. Yes on Math (best per dollar). Not the overall leader.
| Category | Gemini 2.5 Pro | Gemini 3.1 Pro Preview |
|---|---|---|
| General LLM | #61 · Was SOTA · General LLM Margin 41.49659863945578 LMArena leaderboard dataset · Oct 13, 2026 | #15 · Was SOTA · General LLM Margin 10.204081632653057 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #73 · Was SOTA · Reasoning Margin 50.68493150684932 LMArena leaderboard dataset · Oct 13, 2026 | #14 · Was SOTA · Reasoning Margin 10.273972602739732 LMArena leaderboard dataset · Oct 13, 2026 |
| Math | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 | #3 · Near-SOTA · Math Margin 4.444444444444443 Epoch AI benchmarking hub · Feb 19, 2026 |
| Science | #58 · #58 in Science Margin — Epoch AI benchmarking hub · Jun 17, 2025 | #7 · #7 in Science Margin — Epoch AI benchmarking hub · Feb 19, 2026 |
| Coding | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 |
| Coding › Web dev | #105 · #105 in Coding › Web dev Margin 97.19626168224299 LMArena leaderboard dataset · Oct 13, 2026 | #58 · #58 in Coding › Web dev Margin 53.271028037383175 LMArena leaderboard dataset · Oct 13, 2026 |
| Long context | #58 · Was SOTA · Long context Margin 39.455782312925166 LMArena leaderboard dataset · Oct 13, 2026 | #12 · Was SOTA · Long context Margin 8.163265306122454 LMArena leaderboard dataset · Oct 13, 2026 |
| Vision | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 9, 2026 | #25 · Was SOTA · Vision Margin 68.42105263157896 Epoch AI benchmarking hub · Feb 19, 2026 |
| Factuality | #33 · #33 in Factuality Margin 25.373134328358205 LMArena leaderboard dataset · Oct 13, 2026 | #18 · #18 in Factuality Margin 14.179104477611943 LMArena leaderboard dataset · Oct 13, 2026 |
| Abstraction (ARC) | #48 · #48 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Jun 17, 2025 | #2 · #2 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Feb 19, 2026 |
Gemini 2.5 Pro: $3.4375000000000004 per 1M blended tokens.
Gemini 3.1 Pro Preview: $4.5 per 1M blended tokens.
Gemini 2.5 Pro: closed weights.
Gemini 3.1 Pro Preview: closed weights.
General LLM: As of Oct 15, 2026, Gemini 3.1 Pro Preview leads Gemini 2.5 Pro in General LLM at #15 against #61.
Reasoning: As of Oct 15, 2026, Gemini 3.1 Pro Preview leads Gemini 2.5 Pro in Reasoning at #14 against #73.
Science: As of Oct 15, 2026, Gemini 3.1 Pro Preview leads Gemini 2.5 Pro in Science at #7 against #58.
Coding › Web dev: As of Oct 15, 2026, Gemini 3.1 Pro Preview leads Gemini 2.5 Pro in Coding › Web dev at #58 against #105.
Long context: As of Oct 15, 2026, Gemini 3.1 Pro Preview leads Gemini 2.5 Pro in Long context at #12 against #58.
Factuality: As of Oct 15, 2026, Gemini 3.1 Pro Preview leads Gemini 2.5 Pro in Factuality at #18 against #33.
Abstraction (ARC): As of Oct 15, 2026, Gemini 3.1 Pro Preview leads Gemini 2.5 Pro in Abstraction (ARC) at #2 against #48.
Gemini 2.5 Pro · Gemini 3.1 Pro Preview
Gemini 2.5 Pro or Gemini 3.1 Pro Preview?
As of Oct 15, 2026, Gemini 2.5 Pro leads Gemini 3.1 Pro Preview in 0 of 7 shared categories.
Gemini 2.5 Pro or Gemini 3.1 Pro Preview for General LLM?
As of Oct 15, 2026, Gemini 3.1 Pro Preview leads Gemini 2.5 Pro in General LLM at #15 against #61.
Gemini 2.5 Pro or Gemini 3.1 Pro Preview for Reasoning?
As of Oct 15, 2026, Gemini 3.1 Pro Preview leads Gemini 2.5 Pro in Reasoning at #14 against #73.
Gemini 2.5 Pro or Gemini 3.1 Pro Preview for Science?
As of Oct 15, 2026, Gemini 3.1 Pro Preview leads Gemini 2.5 Pro in Science at #7 against #58.