# Is Gemini 3.8 Flash SOTA?

As of Oct 15, 2026, Gemini 3.8 Flash is state of the art on best per dollar in General LLM (since Oct 14, 2026; sources LMArena Text (style-controlled, overall); methodology v1.0).

Yes on General LLM (best per dollar); Reasoning (best per dollar). Not the overall leader.

As of Oct 15, 2026, Gemini 3.8 Flash is state of the art on best per dollar in General LLM (since Oct 14, 2026; sources LMArena Text (style-controlled, overall); methodology v1.0). Gemini 3.8 Flash shares the General LLM best-per-dollar frontier with DeepSeek V4.1 Flash, DeepSeek V4 Flash, Gemini 4 Argon, Mimo V2.6 Flash, Mimo V2.6 Pro tracked since Oct 14, 2026. Co-SOTA shares rank 1.

Methodology v1.0. Computed automatically.

- General LLM: Near-SOTA · General LLM — Close in General LLM: rank #7, 3.7 percentile points behind the leader.
- Reasoning: Near-SOTA · Reasoning — Close in Reasoning: rank #6, 3.7 percentile points behind the leader.
- Math: #5 in Math — Ranked #5 in Math.
- Science: #4 in Science — Last listed at #4 in Science on 2026-09-02. That board does not award a crown.
- Coding: #15 in Coding — Ranked #15 in Coding.
- Coding › Agentic: #15 in Coding › Agentic — Ranked #15 in Coding › Agentic.
- Coding › Web dev: #29 in Coding › Web dev — Ranked #29 in Coding › Web dev.
- Long context: Near-SOTA · Long context — Close in Long context: rank #5, 2.7 percentile points behind the leader.
- Vision: #15 in Vision — Ranked #15 in Vision.
- Factuality: #19 in Factuality — Ranked #19 in Factuality.
- Abstraction (ARC): #1 in Abstraction (ARC) — Last listed at #1 in Abstraction (ARC) on 2026-09-02. That board does not award a crown.

## Long context

https://isitsota.com/c/long-context