Gemini 3.8 Flash vs GPT-4O
As of Oct 15, 2026, Gemini 3.8 Flash leads GPT-4O in 3 of 3 shared categories: Math, Science, and Abstraction (ARC).
Gemini 3.8 Flash
Yes. Yes on General LLM (best per dollar); Reasoning (best per dollar). Not the overall leader.
GPT-4O
It used to be. Was SOTA in General LLM.
| Category | Gemini 3.8 Flash | GPT-4O |
|---|---|---|
| General LLM | #7 · Near-SOTA · General LLM Margin 3.723404255319153 LMArena leaderboard dataset · Oct 13, 2026 | #— · Was SOTA · General LLM Margin — LMArena leaderboard dataset · Feb 21, 2025 |
| Reasoning | #6 · Near-SOTA · Reasoning Margin 3.723404255319153 LMArena leaderboard dataset · Oct 13, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Feb 6, 2025 |
| Math | #5 · #5 in Math Margin 8.888888888888886 Epoch AI benchmarking hub · Sep 2, 2026 | #45 · #45 in Math Margin 100 Epoch AI benchmarking hub · Nov 20, 2024 |
| Science | #4 · #4 in Science Margin — Epoch AI benchmarking hub · Sep 2, 2026 | #131 · #131 in Science Margin — Epoch AI benchmarking hub · Nov 20, 2024 |
| Coding | #15 · #15 in Coding Margin 72.72727272727272 Terminal-Bench Harbor Hub · Oct 6, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Feb 17, 2025 |
| Coding › Agentic | #15 · #15 in Coding › Agentic Margin 72.72727272727272 Terminal-Bench Harbor Hub · Oct 6, 2026 | — |
| Coding › Web dev | #29 · #29 in Coding › Web dev Margin 22.400000000000006 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Long context | #5 · Near-SOTA · Long context Margin 2.659574468085111 LMArena leaderboard dataset · Oct 13, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Jan 22, 2025 |
| Vision | #15 · #15 in Vision Margin 42.10526315789474 Epoch AI benchmarking hub · Sep 2, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 9, 2026 |
| Factuality | #19 · #19 in Factuality Margin 11.6279069767442 LMArena leaderboard dataset · Oct 13, 2026 | #— · Not enough data Margin — Epoch AI benchmarking hub · Aug 6, 2024 |
| Abstraction (ARC) | #1 · #1 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Sep 2, 2026 | #87 · #87 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Nov 20, 2024 |
Gemini 3.8 Flash: $1.5 per 1M blended tokens.
GPT-4O: $4.375000000000001 per 1M blended tokens.
Gemini 3.8 Flash: closed weights.
GPT-4O: closed weights.
Math: As of Oct 15, 2026, Gemini 3.8 Flash leads GPT-4O in Math at #5 against #45.
Science: As of Oct 15, 2026, Gemini 3.8 Flash leads GPT-4O in Science at #4 against #131.
Abstraction (ARC): As of Oct 15, 2026, Gemini 3.8 Flash leads GPT-4O in Abstraction (ARC) at #1 against #87.
Gemini 3.8 Flash or GPT-4O?
As of Oct 15, 2026, Gemini 3.8 Flash leads GPT-4O in 3 of 3 shared categories: Math, Science, and Abstraction (ARC).
Gemini 3.8 Flash or GPT-4O for Math?
As of Oct 15, 2026, Gemini 3.8 Flash leads GPT-4O in Math at #5 against #45.
Gemini 3.8 Flash or GPT-4O for Science?
As of Oct 15, 2026, Gemini 3.8 Flash leads GPT-4O in Science at #4 against #131.
Gemini 3.8 Flash or GPT-4O for Abstraction (ARC)?
As of Oct 15, 2026, Gemini 3.8 Flash leads GPT-4O in Abstraction (ARC) at #1 against #87.