#23Google· released 2026-09-02

Google: Gemini 3.8 Flash.

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

View on OpenRouter ↗
Context
1.0M
Input $/1M
$0.83
Output $/1M
$4.13
Modality
text · image · video · file · audio
Arena Elo
1548
LMArena — human blind votes
AA Index
63.0
Artificial Analysis composite
LiveBench
77.8
Contamination-resistant
GPQA
80.1%
Grad-level science reasoning
MMLU-Pro
84.8%
Broad knowledge
SWE-bench
68.7%
Real GitHub bugs (Verified)
Terminal-Bench
62.4%
Agentic shell tasks
ARC-AGI
13.6%
Abstract reasoning
Aider Polyglot
79.7%
Multi-language code editing
Speed
126 tok/s
Median output speed

Profile

Google: Gemini 3.8 Flash is Google's entry at position #23 on the current aggregated leaderboard. Its strongest signals are graduate-level science reasoning, real-world software engineering, unattended agentic work, and very long context. Every figure below is aggregated from the public sources listed on the homepage and refreshed on each pipeline run.

The score spread is comparatively complete for this model, but the standing advice still applies: treat gaps of a few points as ties and validate on your own workload before committing.

How this model's position is computed is documented in the methodology; what each benchmark actually measures is in the benchmark guide. See a figure that disagrees with its source? Report it — accepted corrections apply on the next refresh.

Nearby on the leaderboard