Gemini Flash
by Google · Model · Language & code models
strong
Gemini 3.8 Flash ranks near the top for image and video understanding
Gemini 3.8 Flash released; beats Opus 5 and GPT 5.6 Sol on finance, legal and agentic terminal coding, state of the art in chart and long-video understanding
AccessAPIPrice$1.50 in / $7.50 out per M tokens
Why we say so
Arena's vision leaderboard puts 3.8 Flash third twice (1315, then 1317), behind only Claude Fable 5 (1326) and Claude Opus 5.5 (1324), a small gap. AI Search uses it as the baseline that Qwen 3.8 Omni Flash and GPT-6 Luna are compared against, and reports Qwen beats it on audio at a lower price. Google's claim that Gemini 4 Hydrogen is 2.5x faster is a maker claim about a different model.
Versions
| Version | Released | Rank |
|---|---|---|
| Gemini 3.8 FlashLATEST strong Third on Arena vision, close behind the Claude models | Sep 2 | |
| Gemini 3.7 Flash | Aug 16 | |
| Gemini 3.6 Flash | Jul 21 |
Evidence
- Nov 9#3 on Arena vision (1317)
- Oct 19#3 on Arena vision (1315)
- Sep 27GPT-6 Luna scores below Gemini 3.8 on the intelligence index
- Sep 6Gemini 3.8 Flash released, third Flash model in six weeks, via Google AI Studio, Gemini API, Antigravity and Gemini app
- Sep 6Ranked number one on DeepSWE for long-horizon software engineering at much lower average cost, but uses by far the most output tokens
Show all 19
- Sep 6Artificial Analysis index ranks it one point below open GLM 5.3 and Kimi K3 and a few below frontier Claude and GPT; about 348 tokens/s
- Sep 6Ranked eighth on Arena but outside the top 10 on LiveBench and below Gemini 3.7 Flash, suggesting benchmark overfitting
- Sep 5Commenters say Gemini 3.8 Flash ranks too high; one reports it gets confused about what it did, another doubts it beats Astra or Fable at code
- Sep 4Driven by Hermes Agent, found and fixed a planted one-line sort bug in a Docker/Postgres/FastAPI stack in 2m12s, with self-verification
- Sep 2On expert-level reasoning benchmark (HLE-Verified), 3.8 Flash narrowly edges out frontier models; Google reports 54.9%
- Sep 2Reported top of the DeepSWE leaderboard, ahead of Opus 5
- Aug 16Gemini 3.7 Flash tops a frontier-code benchmark among small models; 340 tokens/s; in Antigravity, AI Studio, Android Studio, Gemini app
- Aug 16Beats GPT Luna Max on AA index but costs 40 cents per task versus 5 cents for Luna
- Jul 26Google released Gemini 3.6 Flash as the workhorse Flash upgrade, in Gemini API, AI Studio and Antigravity
- Jul 26Artificial Analysis ties 3.6 Flash with 3.5 Flash at slightly lower cost, still pricier than GPT Luna and GLM 5.2
- Jul 22Claimed to beat 3.5 Flash on DeepSWE, OSWorld and MLE-Bench while using fewer tokens per task
- Jul 22Does not claim to beat 3.1 Pro on the hardest long-context reasoning tasks
- Jul 22Via Hermes Agent it found and fixed an unseen berth-depth bug in a FastAPI app without hints
- Jul 22Reviewer thinks its coding quality does not match Fable 5 or Opus, though results were still good
Alternatives
More Gemini Flash
Built on Gemini Flash