Qwen3.5 397B
AlibabaOpen weightsApache 2.0Released Feb 16, 2026
Qwen3.5 397B is not on the arena.ai Agents leaderboard, so it has no rank on our default leaderboard; the other data below is for reference. Qwen3.5 397B ranks #96 on the LMArena Text leaderboard (style control) with an Arena score of 1441.5 (±3.1, 97,678 votes). API price: $0.60 input / $3.60 output per 1M tokens. Context: 262K. Nearest rivals: Grok 4.7 (1442.0) above and GPT-5.2 (1437.4) below.
Quick answer
- Agents leaderboard
- No result yet
- Text (LMArena)
- #96 · 1441.5
- API price (in / out)
- $0.60 / $3.60 per 1M tokens
- Closest rival
- Grok 4.7 · 1442.0
- Cheaper alternative
- Qwen3.7 Plus: Text 1455.3, output $1.60 (56% cheaper)
- Data updated
- Nov 10, 2026 · synced daily
Sources: arena.ai, LMArena, Artificial Analysis, OpenRouter
Key metrics
Models ranked nearby
Sorted by Arena score| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 54 |  Kimi K2.5 | 1449.5 | – | $3.00 | – |
| 55 |  Gemini 2.5 Pro | 1445.5 | – | $10.00 | – |
| 56 |  Grok 4.7 | 1442.0 | 35.5 | $6.00 | 58 |
| 57 | Qwen3.5 397BThis page | 1441.5 | – | $3.60 | – |
| 58 |  GPT-5.2 | 1437.4 | – | $14.00 | – |
| 59 |  MiniMax M3 | 1435.9 | 18.9 | $1.20 | 106 |
| 60 |  DeepSeek V4 Flash | 1435.8 | – | $0.28 | – |
More from Alibaba
| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 21 | Qwen3.8 Max | 1484.0 | 33.7 | $6.00 | 38 |
| 34 | Qwen3.7 Max | 1473.8 | – | $7.50 | – |
| 46 | Qwen3.6 Max | 1459.7 | – | – | – |
| 51 | Qwen3.7 Plus | 1455.3 | – | $1.60 | 58 |
| 62 | Qwen3.8 27B | 1433.4 | 20.1 | $3.00 | 38 |
| 66 | Qwen3 Max | 1423.3 | – | – | – |
Pricing
- No official list price; OpenRouter price is $0.60 input and $3.60 output per 1M tokens (USD).
- At a typical 3:1 input-to-output ratio, the blended cost is about $1.35 per 1M tokens.
- Among 79 models with an output price, it is the #27 cheapest.
- The cheapest OpenRouter route charges $0.60 input / $3.60 output.
Sources & methodology
Qwen3.5 397B is not on the arena.ai Agents leaderboard, so it has no rank on our default leaderboard; the other data below is for reference.
- 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
What rank is Qwen3.5 397B right now?
Qwen3.5 397B is #57 on our leaderboard of 70 scored models (Arena score 1441.5); its raw LMArena rank is #96.
What does Qwen3.5 397B cost via API?
Input $0.60 / output $3.60 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 $1.35 per 1M tokens.
How close is Qwen3.5 397B to the models ranked next to it?
It is 0.5 points behind Grok 4.7 (1442.0) and 4.1 points ahead of GPT-5.2 (1437.4); gaps smaller than the confidence interval (±3.1) are not significant.
Is Qwen3.5 397B open source? Can it be self-hosted?
Qwen3.5 397B is an open-weights model (license: Apache 2.0); you can download the weights and self-host.
What is the context length of Qwen3.5 397B?
262K (262,144 tokens, as listed on OpenRouter).
Qwen3.5 397B vs Grok 4.7: which is better?
On the LMArena Text leaderboard Qwen3.5 397B scores 1441.5 and Grok 4.7 scores 1442.0 (a 0.5-point gap, within the confidence interval, so not significant). On price, Qwen3.5 397B costs $3.60 and Grok 4.7 $6.00 per 1M output tokens.
Is there a cheaper model close to Qwen3.5 397B?
Yes: Qwen3.7 Plus scores 1455.3 on the Text leaderboard (Qwen3.5 397B: 1441.5) and costs $1.60 per 1M output tokens, about 56% less than Qwen3.5 397B ($3.60).
Where does the Qwen3.5 397B 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 10, 2026.