Gemini 3.8 Flash vs GPT-5 Mini
As of Oct 14, 2026, Gemini 3.8 Flash leads GPT-5 Mini in 7 of 7 shared categories: General LLM, Reasoning, Math, Science, Long context, Factuality, and Abstraction (ARC).
Gemini 3.8 Flash
Yes. Yes on General LLM (best per dollar); Reasoning (best per dollar). Not the overall leader.
GPT-5 Mini
It used to be. Was SOTA in Math.
| Category | Gemini 3.8 Flash | GPT-5 Mini |
|---|---|---|
| General LLM | #7 · Was SOTA · General LLM Margin 4.761904761904759 LMArena leaderboard dataset · Oct 13, 2026 | #128 · #128 in General LLM Margin 87.07482993197279 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #6 · #6 in Reasoning Margin 4.794520547945211 LMArena leaderboard dataset · Oct 13, 2026 | #130 · #130 in Reasoning Margin 89.72602739726028 LMArena leaderboard dataset · Oct 13, 2026 |
| Math | #5 · #5 in Math Margin 8.888888888888886 Epoch AI benchmarking hub · Sep 2, 2026 | #21 · Was SOTA · Math Margin 44.44444444444444 Epoch AI benchmarking hub · Aug 7, 2025 |
| Science | #4 · #4 in Science Margin — Epoch AI benchmarking hub · Sep 2, 2026 | #81 · #81 in Science Margin — Epoch AI benchmarking hub · Aug 7, 2025 |
| Coding | #15 · #15 in Coding Margin 72.72727272727272 Terminal-Bench Harbor Hub · Oct 6, 2026 | #— · Not enough data Margin — Epoch AI benchmarking hub · Aug 7, 2025 |
| Coding › Agentic | #15 · #15 in Coding › Agentic Margin 72.72727272727272 Terminal-Bench Harbor Hub · Oct 6, 2026 | — |
| Coding › Web dev | #27 · #27 in Coding › Web dev Margin 24.29906542056075 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Long context | #5 · Near-SOTA · Long context Margin 3.401360544217681 LMArena leaderboard dataset · Oct 13, 2026 | #146 · #146 in Long context Margin 99.31972789115646 LMArena leaderboard dataset · Oct 13, 2026 |
| 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 | #17 · #17 in Factuality Margin 13.43283582089552 LMArena leaderboard dataset · Oct 13, 2026 | #110 · #110 in Factuality Margin 82.83582089552239 LMArena leaderboard dataset · Oct 13, 2026 |
| Abstraction (ARC) | #1 · #1 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Sep 2, 2026 | #41 · #41 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Aug 7, 2025 |
Gemini 3.8 Flash: $1.5 per 1M blended tokens.
GPT-5 Mini: $0.6875 per 1M blended tokens.
Gemini 3.8 Flash: closed weights.
GPT-5 Mini: closed weights.
General LLM: As of Oct 14, 2026, Gemini 3.8 Flash leads GPT-5 Mini in General LLM at #7 against #128.
Reasoning: As of Oct 14, 2026, Gemini 3.8 Flash leads GPT-5 Mini in Reasoning at #6 against #130.
Math: As of Oct 14, 2026, Gemini 3.8 Flash leads GPT-5 Mini in Math at #5 against #21.
Science: As of Oct 14, 2026, Gemini 3.8 Flash leads GPT-5 Mini in Science at #4 against #81.
Long context: As of Oct 14, 2026, Gemini 3.8 Flash leads GPT-5 Mini in Long context at #5 against #146.
Factuality: As of Oct 14, 2026, Gemini 3.8 Flash leads GPT-5 Mini in Factuality at #17 against #110.
Abstraction (ARC): As of Oct 14, 2026, Gemini 3.8 Flash leads GPT-5 Mini in Abstraction (ARC) at #1 against #41.
Gemini 3.8 Flash or GPT-5 Mini?
As of Oct 14, 2026, Gemini 3.8 Flash leads GPT-5 Mini in 7 of 7 shared categories: General LLM, Reasoning, Math, Science, Long context, Factuality, and Abstraction (ARC).
Gemini 3.8 Flash or GPT-5 Mini for General LLM?
As of Oct 14, 2026, Gemini 3.8 Flash leads GPT-5 Mini in General LLM at #7 against #128.
Gemini 3.8 Flash or GPT-5 Mini for Reasoning?
As of Oct 14, 2026, Gemini 3.8 Flash leads GPT-5 Mini in Reasoning at #6 against #130.
Gemini 3.8 Flash or GPT-5 Mini for Math?
As of Oct 14, 2026, Gemini 3.8 Flash leads GPT-5 Mini in Math at #5 against #21.