Qwen3.8 Max
AlibabaProprietaryReleased Sep 2, 2026
On the arena.ai Agents leaderboard, Qwen3.8 Max has a Net Improvement of 0.33% (—, rank #29, 95% interval -0.34%–0.99%). Qwen3.8 Max ranks #23 on the LMArena Text leaderboard (style control) with an Arena score of 1484.2 (±4.7, 35,805 votes). Artificial Analysis Intelligence Index: 33.7. API price: $2.00 input / $6.00 output per 1M tokens. Context: 1M. Nearest rivals: GPT-5.6 Sol (1485.0) above and Gemini 3.6 Flash (1482.7) below.
Quick answer
- Agents leaderboard
- #29 of 37 · 0.33% success
- Text (LMArena)
- #23 · 1484.2
- 17NAS overall
- #24 of 36
- API price (in / out)
- $2.00 / $6.00 per 1M tokens
- Closest rival
- GPT-5.6 Sol · 1485.0
- Cheaper alternative
- Gemini 3.8 Flash: Text 1497.5, output $3.75 (38% cheaper)
- Data updated
- Nov 9, 2026 · synced daily
Sources: arena.ai, LMArena, Artificial Analysis, OpenRouter
Key metrics
Rank history
LMArena rank, last 25 days#24 on Oct 16, #23 now; best #23 in this period.
Models ranked nearby
Sorted by Arena score| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 17 | 1486.8 | – | $12.00 | 128 | |
| 18 | 1485.5 | – | $12.00 | – | |
| 19 | 1485.0 | – | $20.00 | – | |
| 20 | 1484.2 | 33.7 | $6.00 | 38 | |
| 21 | 1482.7 | – | $3.75 | – | |
| 22 | 1482.6 | 31.7 | $4.40 | 71 | |
| 23 | 1482.0 | – | $25.00 | – |
More from Alibaba
| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 33 | 1473.8 | – | $7.50 | – | |
| 45 | 1459.6 | – | – | – | |
| 50 | 1455.4 | – | $1.60 | 58 | |
| 63 | 1423.4 | – | – | – |
Pricing
- Official API list price: $2.00 input and $6.00 output per 1M tokens (USD).
- At a typical 3:1 input-to-output ratio, the blended cost is about $3.00 per 1M tokens.
- Among 68 models with an output price, it is the #31 cheapest.
- The cheapest OpenRouter route charges $2.00 input / $6.00 output.
Sources & methodology
On the arena.ai Agents leaderboard, Qwen3.8 Max has a Net Improvement of 0.33% (—, rank #29, 95% interval -0.34%–0.99%).
- arena.ai Agents — agent Net Improvement, 95% interval, sessions and rank (via the public Hugging Face dataset, CC BY 4.0).
- LMArena — Arena score (Text leaderboard with style control, the same view arena.ai shows by default), 95% confidence interval, votes and rank.
- Artificial Analysis — Intelligence / Coding Index, output speed and latency (medians).
- OpenRouter — Route prices, context length and listing date.
Arena scores use the Bradley-Terry model (not Elo); ± is the half-width of the 95% confidence interval. Latency figures are Artificial Analysis medians; for reasoning models, time to first token and to first answer include the thinking phase. Data syncs daily at 14:20 (UTC+8).
Limits: Arena scores come from anonymous users voting on chats, so they reflect conversational preference rather than agent or coding benchmarks; with few votes the interval is wide and ranks move. Prices and speeds change as providers update them.
FAQ
How does Qwen3.8 Max do on the Agents leaderboard?
On the arena.ai Agents leaderboard, Qwen3.8 Max has a Net Improvement of 0.33% (—, rank #29, 95% interval -0.34%–0.99%).
What rank is Qwen3.8 Max right now?
Qwen3.8 Max is #20 on our leaderboard of 64 scored models (Arena score 1484.2); its raw LMArena rank is #23.
What does Qwen3.8 Max cost via API?
Input $2.00 / output $6.00 per 1M tokens (official API list price; the OpenRouter quote when no official price is available). At a typical 3:1 input-to-output ratio, the blended cost is about $3.00 per 1M tokens.
How fast is Qwen3.8 Max?
Artificial Analysis measures about 38 output tokens per second, 2.0 s to the first token and 55 s to the first answer token; it is a reasoning model, so latency includes thinking time.
How close is Qwen3.8 Max to the models ranked next to it?
It is 0.8 points behind GPT-5.6 Sol (1485.0) and 1.5 points ahead of Gemini 3.6 Flash (1482.7); gaps smaller than the confidence interval (±4.7) are not significant.
Is Qwen3.8 Max open source? Can it be self-hosted?
Qwen3.8 Max is a closed model, available only via official APIs or hosted services.
What is the context length of Qwen3.8 Max?
1M (1,000,000 tokens, as listed on OpenRouter).
Qwen3.8 Max vs GPT-5.6 Sol: which is better?
On the LMArena Text leaderboard Qwen3.8 Max scores 1484.2 and GPT-5.6 Sol scores 1485.0 (a 0.8-point gap, within the confidence interval, so not significant). Agent task success: Qwen3.8 Max 0.33%, GPT-5.6 Sol 4.53%. On price, Qwen3.8 Max costs $6.00 and GPT-5.6 Sol $20.00 per 1M output tokens.
Is there a cheaper model close to Qwen3.8 Max?
Yes: Gemini 3.8 Flash scores 1497.5 on the Text leaderboard (Qwen3.8 Max: 1484.2) and costs $3.75 per 1M output tokens, about 38% less than Qwen3.8 Max ($6.00).
Where does the Qwen3.8 Max data come from and how often is it updated?
Agent success rates come from the arena.ai Agents leaderboard (CC BY 4.0), Text scores from LMArena, intelligence and speed from Artificial Analysis, and prices and context from official list prices and OpenRouter. 17NAS syncs daily at 06:20 UTC; this page was last updated Nov 9, 2026.