Gemini 3.8 Flash vs Claude Sonnet 5
Gemini 3.8 Flash comes out ahead on 10 of 12 shared measures, and the two rank 13 and 37 of 51 overall. Gemini 3.8 Flash is 2.7× cheaper per million tokens (blended) — A$3.69 vs A$9.83 per 1,000 replies of customer support replys.
Where each one wins.
Gemini 3.8 Flash ranks 13th of 51; Claude Sonnet 5 ranks 37th.
Gemini 3.8 Flash ranks 12th of 42; Claude Sonnet 5 ranks 22nd.
Gemini 3.8 Flash ranks 10th of 41; Claude Sonnet 5 ranks 19th.
Gemini 3.8 Flash ranks 12th of 51; Claude Sonnet 5 ranks 27th.
Claude Sonnet 5 ranks 14th of 51; Gemini 3.8 Flash ranks 20th.
Gemini 3.8 Flash ranks 14th of 50; Claude Sonnet 5 ranks 33rd.
Gemini 3.8 Flash is 2.7× cheaper per million tokens (blended) — A$3.69 vs A$9.83 per 1,000 replies of customer support replys.
Gemini 3.8 Flash writes 4.2× faster (305 tok/s vs 73 tok/s).
Both can be used from Australia through their makers’ own APIs (Google and Anthropic), which may process requests outside 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. Claude Sonnet 5 can run with requests kept in Australia on AWS Bedrock in Melbourne.
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 | GEMINI 3.8 FLASH | CLAUDE SONNET 5 | LEADS |
|---|---|---|---|
| AA Intelligence Index | 40.9 | 38.2 | Gemini 3.8 Flash |
| AA Coding Index | 76.3 | 71.5 | Gemini 3.8 Flash |
| GPQA Diamond | 95.3% | 91.1% | Gemini 3.8 Flash |
| Humanity’s Last Exam | 47.8% | 41.3% | Gemini 3.8 Flash |
| AA-LCR | 81.3% | 82.0% | Claude Sonnet 5 |
| Terminal-Bench 2.1 | 87.6% | 80.5% | Gemini 3.8 Flash |
| τ²-Bench (banking) | 44.9% | 37.3% | Gemini 3.8 Flash |
| SciCode | 56.6% | 54.3% | Gemini 3.8 Flash |
| LMArena Text | 1493 | 1461 | Gemini 3.8 Flash |
| LMArena WebDev | 1583 | 1538 | Gemini 3.8 Flash |
| LMArena Vision | 1266 | ||
| LMArena Document | 1476 | ||
| LMArena Search | 1196 | ||
| LMArena Agent | #13 | #9 | Claude Sonnet 5 |
| Blended price (AUD) | A$2.11 | A$5.62 | Gemini 3.8 Flash |
| Output speed | 305 tok/s | 73 tok/s | Gemini 3.8 Flash |
| Answer starts after | 12 s | 1.4 min | Gemini 3.8 Flash |
| Context window | 1,048,576 tokens | 1,000,000 tokens | Gemini 3.8 Flash |
| USE FROM AUSTRALIA | |||
| Maker’s API | YES | YES | |
| Processed in Australia | NO | YES · CLOUD | |
| AUSTRALIAN CLOUD REGIONS | |||
| AWS Bedrock · Sydney | NOT OFFERED | GLOBAL | |
| AWS Bedrock · Melbourne | NOT OFFERED | IN REGION | |
| Azure · Australia East | NOT OFFERED | NOT IN AU | |
| Google Vertex AI · Sydney | GLOBAL | GLOBAL | |
The same jobs, in Australian dollars.
List prices at the snapshot’s RBA rate, excluding GST and reasoning tokens.
| JOB | GEMINI 3.8 FLASH | CLAUDE SONNET 5 | MEDIAN MODEL |
|---|---|---|---|
| Customer support replyPER 1,000 REPLIES | A$3.69 | A$9.83 | ≈ A$6.58 |
| Summarise a 30-page documentPER 100 DOCUMENTS | A$2.53 | A$6.74 | ≈ A$4.74 |
| Agentic coding taskPER 10 TASKS | A$2.00 | A$5.33 | ≈ A$3.72 |
Each model in full.
Gemini 3.8 Flash or Claude Sonnet 5?
Is Gemini 3.8 Flash better than Claude Sonnet 5?
On our overall leaderboard Gemini 3.8 Flash ranks 13th and Claude Sonnet 5 37th of 51. Which is better depends on the job: the table above compares each benchmark, price and Australian availability.
Which is cheaper, Gemini 3.8 Flash or Claude Sonnet 5?
Gemini 3.8 Flash, at A$2.11 per million tokens (blended) against A$5.62 for Claude Sonnet 5. Reasoning-heavy settings add output tokens, so real bills depend on the effort level you run.
Can I use Gemini 3.8 Flash and Claude Sonnet 5 in Australia?
Both can be used from Australia through their makers’ own APIs (Google and Anthropic), which may process requests outside 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. Claude Sonnet 5 can run with requests kept in Australia on AWS Bedrock in Melbourne.
Ratings: LMArena leaderboard dataset (CC BY 4.0), rescaled for the lens scores · leaderboards to 22 Sep 2026
Evaluations, prices and speed: Artificial Analysis (artificialanalysis.ai) · fetched 23 Sep 2026
Exchange rate: Reserve Bank of Australia, table F11.1 · A$1 = US$0.7123 on 22 Sep 2026 · prices exclude GST
Snapshot 23 Sep 2026 · updated weekly · How the rankings work →