LLM compare · detail

Gemini 3.5 Flash

Provider: Google

Model type: specialist Budget: mid-budget Use it for: large batches Use it for: company knowledge Use it for: fast replies

batch pick backed by current AA.

Verdict „Gemini 3.5 Flash has IQ 55.3 and input $1.5/M and DeepSWE pass@1 28.3 % in the sources. Consider it for large batches, company knowledge; for deep-coding, real-time-latency, run a second benchmark before rollout."

Snapshot summary

Google positions Gemini as a model layer for its cloud, workspace and multimodal ecosystem, so it covers text, large context, video, audio and vision. Gemini 3.5 Flash is the faster and cheaper Gemini worker layer. It fits routing, extraction, batch jobs and tasks where latency and cost beat absolute reasoning.

In this compare snapshot it is tagged mainly for batch, rag, real-time, with price tier mid and context window není v ověřených datech. The negative side matters too: watch deep-coding, real-time-latency. Use the numbers below as the hard boundary, because this profile explains the model, it does not replace benchmark provenance.

Figures below, fetched from source artificial_analysis (fetched 2026-06-14T04:00:40Z).

Snapshot figures

$1.5/M input artificial_analysis:gemini-3-5-flash

$9/M output artificial_analysis:gemini-3-5-flash

55.3 intelligence index artificial_analysis:gemini-3-5-flash

28.3% DeepSWE pass@1 deepswe:gemini-3-5-flash

56.6% DeepSWE pass@4 · medium deepswe:gemini-3-5-flash

What this means

✓ Good for: batch · rag · real-time

✗ Not for: deep-coding · real-time-latency

Source and provenance

Data source: artificial_analysis
Fetched: 2026-06-14T04:00:40Z
Status per metric: price: artificial_analysis:gemini-3-5-flash; IQ: artificial_analysis:gemini-3-5-flash; Elo: curated_seed; Aider: curated_seed; DeepSWE: deepswe:gemini-3-5-flash

This page shows only verified data from the current snapshot.