Qwen3.8 Max vs Kimi K3
Kimi K3 comes out ahead on 6 of 12 shared measures, and the two rank 15 and 16 of 51 overall. Qwen3.8 Max is 2.0× cheaper per million tokens (blended) — A$8.14 vs A$14.74 per 1,000 replies of customer support replys.
Where each one wins.
Kimi K3 ranks 15th of 51; Qwen3.8 Max ranks 16th.
Qwen3.8 Max ranks 4th of 42; Kimi K3 ranks 5th.
Qwen3.8 Max ranks 7th of 41; Kimi K3 ranks 9th.
Kimi K3 ranks 11th of 51; Qwen3.8 Max ranks 13th.
Kimi K3 ranks 1st of 51; Qwen3.8 Max ranks 27th.
Qwen3.8 Max ranks 13th of 50; Kimi K3 ranks 27th.
Qwen3.8 Max is 2.0× cheaper per million tokens (blended) — A$8.14 vs A$14.74 per 1,000 replies of customer support replys.
Qwen3.8 Max writes 1.1× faster (42 tok/s vs 38 tok/s).
Both can be used from Australia through their makers’ own APIs (Alibaba and Moonshot AI), which may process requests outside Australia. None of the major cloud platforms offer it in an Australian region yet. Kimi K3 can be called from AWS Bedrock in Sydney and Melbourne, 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.
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 | QWEN3.8 MAX | KIMI K3 | LEADS |
|---|---|---|---|
| AA Intelligence Index | 45.4 | 43.6 | Qwen3.8 Max |
| AA Coding Index | 76.2 | 76.2 | Level |
| GPQA Diamond | 92.8% | 93.5% | Kimi K3 |
| Humanity’s Last Exam | 43.1% | 46.9% | Kimi K3 |
| AA-LCR | 80.3% | 88.7% | Kimi K3 |
| Terminal-Bench 2.1 | 88.8% | 85.0% | Qwen3.8 Max |
| τ²-Bench (banking) | 47.8% | 46.0% | Qwen3.8 Max |
| SciCode | 52.1% | 59.5% | Kimi K3 |
| LMArena Text | 1481 | 1485 | Level |
| LMArena WebDev | 1671 | 1658 | Level |
| LMArena Vision | 1302 | ||
| LMArena Agent | #17 | #8 | Kimi K3 |
| Blended price (AUD) | A$4.21 | A$8.42 | Qwen3.8 Max |
| Output speed | 42 tok/s | 38 tok/s | Qwen3.8 Max |
| Answer starts after | 50 s | 56 s | Qwen3.8 Max |
| Context window | 1,000,000 tokens | 1,048,576 tokens | Kimi K3 |
| USE FROM AUSTRALIA | |||
| Maker’s API | YES | YES | |
| Processed in Australia | NO | SELF-HOST ONLY | |
| AUSTRALIAN CLOUD REGIONS | |||
| AWS Bedrock · Sydney | NOT OFFERED | GLOBAL | |
| AWS Bedrock · Melbourne | NOT OFFERED | GLOBAL | |
| Azure · Australia East | NOT OFFERED | NOT OFFERED | |
| Google Vertex AI · Sydney | NOT OFFERED | NOT OFFERED | |
The same jobs, in Australian dollars.
List prices at the snapshot’s RBA rate, excluding GST and reasoning tokens.
| JOB | QWEN3.8 MAX | KIMI K3 | MEDIAN MODEL |
|---|---|---|---|
| Customer support replyPER 1,000 REPLIES | A$8.14 | A$14.74 | ≈ A$6.58 |
| Summarise a 30-page documentPER 100 DOCUMENTS | A$6.29 | A$10.11 | ≈ A$4.74 |
| Agentic coding taskPER 10 TASKS | A$4.89 | A$8.00 | ≈ A$3.72 |
Each model in full.
Qwen3.8 Max or Kimi K3?
Is Qwen3.8 Max better than Kimi K3?
On our overall leaderboard Kimi K3 ranks 15th and Qwen3.8 Max 16th of 51. Which is better depends on the job: the table above compares each benchmark, price and Australian availability.
Which is cheaper, Qwen3.8 Max or Kimi K3?
Qwen3.8 Max, at A$4.21 per million tokens (blended) against A$8.42 for Kimi K3. Reasoning-heavy settings add output tokens, so real bills depend on the effort level you run.
Can I use Qwen3.8 Max and Kimi K3 in Australia?
Both can be used from Australia through their makers’ own APIs (Alibaba and Moonshot AI), which may process requests outside Australia. None of the major cloud platforms offer it in an Australian region yet. Kimi K3 can be called from AWS Bedrock in Sydney and Melbourne, 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.
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 →