Gemini 3 Pro vs GPT-5.4 Mini
As of Oct 15, 2026, Gemini 3 Pro leads GPT-5.4 Mini in 5 of 5 shared categories: General LLM, Reasoning, Coding › Web dev, Long context, and Factuality.
Gemini 3 Pro
It used to be. Was SOTA in General LLM.
GPT-5.4 Mini
#36 Best recorded rank: #36 in Abstraction (ARC), as of Oct 15, 2026.
| Category | Gemini 3 Pro | GPT-5.4 Mini |
|---|---|---|
| General LLM | #16 · Was SOTA · General LLM Margin 8.510638297872347 LMArena leaderboard dataset · Oct 13, 2026 | #75 · #75 in General LLM Margin 39.8936170212766 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #23 · Was SOTA · Reasoning Margin 12.765957446808514 LMArena leaderboard dataset · Oct 13, 2026 | #74 · #74 in Reasoning Margin 39.8936170212766 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 | — | #52 · #52 in Science Margin — Epoch AI benchmarking hub · Mar 17, 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 | #65 · Was SOTA · Coding › Web dev Margin 51.2 LMArena leaderboard dataset · Oct 13, 2026 | #81 · #81 in Coding › Web dev Margin 64 LMArena leaderboard dataset · Oct 13, 2026 |
| Long context | #24 · Was SOTA · Long context Margin 12.765957446808514 LMArena leaderboard dataset · Oct 13, 2026 | #87 · #87 in Long context Margin 46.27659574468085 LMArena leaderboard dataset · Oct 13, 2026 |
| Vision | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 9, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 9, 2026 |
| Factuality | #10 · Was SOTA · Factuality Margin 6.395348837209298 LMArena leaderboard dataset · Oct 13, 2026 | #65 · #65 in Factuality Margin 38.372093023255815 LMArena leaderboard dataset · Oct 13, 2026 |
| Abstraction (ARC) | — | #36 · #36 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Mar 17, 2026 |
Gemini 3 Pro: price per 1M tokens is unset in the catalog.
GPT-5.4 Mini: $1.6875 per 1M blended tokens.
Gemini 3 Pro: closed weights.
GPT-5.4 Mini: closed weights.
General LLM: As of Oct 15, 2026, Gemini 3 Pro leads GPT-5.4 Mini in General LLM at #16 against #75.
Reasoning: As of Oct 15, 2026, Gemini 3 Pro leads GPT-5.4 Mini in Reasoning at #23 against #74.
Coding › Web dev: As of Oct 15, 2026, Gemini 3 Pro leads GPT-5.4 Mini in Coding › Web dev at #65 against #81.
Long context: As of Oct 15, 2026, Gemini 3 Pro leads GPT-5.4 Mini in Long context at #24 against #87.
Factuality: As of Oct 15, 2026, Gemini 3 Pro leads GPT-5.4 Mini in Factuality at #10 against #65.
Gemini 3 Pro or GPT-5.4 Mini?
As of Oct 15, 2026, Gemini 3 Pro leads GPT-5.4 Mini in 5 of 5 shared categories: General LLM, Reasoning, Coding › Web dev, Long context, and Factuality.
Gemini 3 Pro or GPT-5.4 Mini for General LLM?
As of Oct 15, 2026, Gemini 3 Pro leads GPT-5.4 Mini in General LLM at #16 against #75.
Gemini 3 Pro or GPT-5.4 Mini for Reasoning?
As of Oct 15, 2026, Gemini 3 Pro leads GPT-5.4 Mini in Reasoning at #23 against #74.
Gemini 3 Pro or GPT-5.4 Mini for Coding › Web dev?
As of Oct 15, 2026, Gemini 3 Pro leads GPT-5.4 Mini in Coding › Web dev at #65 against #81.