DeepSeek V4 Flash vs Gemini 3.8 Flash
Gemini 3.8 Flash comes out ahead on 10 of 11 shared measures, and the two rank 13 and 37 of 54 overall. DeepSeek V4 Flash is 2.3× cheaper per million tokens (blended) — A$1.84 vs A$3.78 per 1,000 replies of customer support replys.
Where each one wins.
Gemini 3.8 Flash ranks 13th of 54; DeepSeek V4 Flash ranks 37th.
Gemini 3.8 Flash ranks 12th of 42; DeepSeek V4 Flash ranks 24th.
Gemini 3.8 Flash ranks 10th of 41; DeepSeek V4 Flash ranks 21st.
Gemini 3.8 Flash ranks 15th of 54; DeepSeek V4 Flash ranks 38th.
Gemini 3.8 Flash ranks 22nd of 54; DeepSeek V4 Flash ranks 32nd.
Gemini 3.8 Flash ranks 17th of 53; DeepSeek V4 Flash ranks 19th.
DeepSeek V4 Flash is 2.3× cheaper per million tokens (blended) — A$1.84 vs A$3.78 per 1,000 replies of customer support replys.
Gemini 3.8 Flash writes 1.1× faster (244 tok/s vs 224 tok/s).
Both can be used from Australia through their makers’ own APIs (DeepSeek and Google), which may process requests outside Australia. DeepSeek V4 Flash can be called from Microsoft Azure in Australia East, but only through global routing, so requests may be processed outside Australia; its weights are public, so it can also be self-hosted in Australia. Gemini 3.8 Flash can be called from Google Vertex AI in Sydney, but only through global routing, so requests may be processed outside Australia.
Side by side.
“Level” means the gap is inside LMArena’s confidence interval, or the scores are identical. Independent test scores are for each model’s headline setting. Both models can be used from Australia through their makers’ APIs; the Australian rows show whether requests can also be processed in Australia.
| BENCHMARK | DEEPSEEK V4 FLASH | GEMINI 3.8 FLASH | LEADS |
|---|---|---|---|
| AA Intelligence Index | 34.3 | 40.9 | Gemini 3.8 Flash |
| AA Coding Index | 69.1 | 76.3 | Gemini 3.8 Flash |
| GPQA Diamond | 90.8% | 95.3% | Gemini 3.8 Flash |
| Humanity’s Last Exam | 38.6% | 47.8% | Gemini 3.8 Flash |
| AA-LCR | 79.7% | 81.3% | Gemini 3.8 Flash |
| Terminal-Bench 2.1 | 78.7% | 87.6% | Gemini 3.8 Flash |
| τ²-Bench (banking) | 39.4% | 44.9% | Gemini 3.8 Flash |
| SciCode | 50.3% | 56.6% | Gemini 3.8 Flash |
| LMArena Text | 1494 | ||
| LMArena WebDev | 1581 | 1583 | Level |
| LMArena Vision | 1286 | ||
| LMArena Agent | #22 | #19 | Gemini 3.8 Flash |
| Blended price (AUD) | A$0.95 | A$2.16 | DeepSeek V4 Flash |
| Output speed | 224 tok/s | 244 tok/s | Gemini 3.8 Flash |
| Answer starts after | 9.8 s | 14 s | DeepSeek V4 Flash |
| Context window | 1,000,000 tokens | 1,048,576 tokens | Gemini 3.8 Flash |
| USE FROM AUSTRALIA | |||
| Maker’s API | YES | YES | |
| Processed in Australia | SELF-HOST ONLY | NO | |
| AUSTRALIAN CLOUD REGIONS | |||
| AWS Bedrock · Sydney | NOT OFFERED | NOT OFFERED | |
| AWS Bedrock · Melbourne | NOT OFFERED | NOT OFFERED | |
| Azure · Australia East | GLOBAL | NOT OFFERED | |
| Google Vertex AI · Sydney | NOT OFFERED | GLOBAL | |
The same jobs, in Australian dollars.
List prices at the snapshot’s RBA rate, excluding GST and reasoning tokens.
| JOB | DEEPSEEK V4 FLASH | GEMINI 3.8 FLASH | MEDIAN MODEL |
|---|---|---|---|
| Customer support replyPER 1,000 REPLIES | A$1.84 | A$3.78 | ≈ A$8.20 |
| Summarise a 30-page documentPER 100 DOCUMENTS | A$1.42 | A$2.59 | ≈ A$5.35 |
| Agentic coding taskPER 10 TASKS | A$1.10 | A$2.05 | ≈ A$4.27 |
Each model in full.
DeepSeek V4 Flash or Gemini 3.8 Flash?
Is DeepSeek V4 Flash better than Gemini 3.8 Flash?
On our overall leaderboard Gemini 3.8 Flash ranks 13th and DeepSeek V4 Flash 37th of 54. Which is better depends on the job: the table above compares each benchmark, price and Australian availability.
Which is cheaper, DeepSeek V4 Flash or Gemini 3.8 Flash?
DeepSeek V4 Flash, at A$0.95 per million tokens (blended) against A$2.16 for Gemini 3.8 Flash. Reasoning-heavy settings add output tokens, so real bills depend on the effort level you run.
Can I use DeepSeek V4 Flash and Gemini 3.8 Flash in Australia?
Both can be used from Australia through their makers’ own APIs (DeepSeek and Google), which may process requests outside Australia. DeepSeek V4 Flash can be called from Microsoft Azure in Australia East, but only through global routing, so requests may be processed outside Australia; its weights are public, so it can also be self-hosted in Australia. Gemini 3.8 Flash can be called from Google Vertex AI in Sydney, but only through global routing, so requests may be processed outside Australia.
Ratings: LMArena leaderboard dataset (CC BY 4.0), rescaled for the lens scores · leaderboards to 30 Sep 2026
Evaluations, prices and speed: Artificial Analysis (artificialanalysis.ai) · fetched 1 Oct 2026
Exchange rate: Reserve Bank of Australia, table F11.1 · A$1 = US$0.6949 on 1 Oct 2026 · prices exclude GST
Snapshot 2 Oct 2026 · updated weekly · How the rankings work →