Qwen3.8 Flash Next qwen3.8-flash-next
qwen · qwen
#5 overall
- params
- 180B
- arch
- moe
- license
- other open weights
- released
- Aug 2026
- downloads/30d
- 3.1M
# architecture
- layers
- 48
- d_model
- 2560
- heads
- 24q / 2kv
- head dim
- 256
- experts
- top-10 of 512
- vocab
- 248320
- family
- qwen4_exp_text
signal path of one layer, generated from the registry's structured fields — dimension lines quote the model's real numbers; an MoE trace forks at the router, a dense trace runs straight through. Geometry fields come from the repo's config.json.
# why ranked
Overall: #5 — score 95.4 ● low — a single signal; treat with caution
| signal | weight | input (0–100) |
|---|---|---|
| aa_intelligence | 0.70 | 93.5 |
| bench_composite | 0.30 | 100.0 |
benchmark panel evidence:
| complete panel | score (0–100) |
|---|---|
| aa-coding-v1 | 100.0 |
Coding: provisional — score 97.1 ● low — a single signal; treat with caution
provisional: too few independent signals for a numbered position — the score is shown, but this model sorts after every ranked model.
| signal | weight | input (0–100) |
|---|---|---|
| aa_coding | 0.30 | 97.1 |
| aider_polyglot | 0.30 | — |
| swe_bench_verified | 0.40 | — |
missing signals are dropped and the remaining weights renormalized — never imputed.
# trend
methodology changed during this history window; score movement across that boundary is not model movement. See methodology v6.
# benchmarks
| benchmark | score | source | date |
|---|---|---|---|
| AA Coding Index | 73.1 | Artificial Analysis | — |
| AA Intelligence Index | 39.8 | Artificial Analysis | — |
| Agents-last-exam | 0.5 / 1 | LLM Stats | — |
| Androidworld | 0.8 / 1 | LLM Stats | — |
| Charxiv-r | 0.9 / 1 | LLM Stats | — |
| Claw-eval-mm | 0.6 / 1 | LLM Stats | — |
| LMArena Elo (Code) | 1632.0 | LMArena | Oct 2026 |
# where to run
| provider | quant | ctx | $/M in | $/M out | $/M cache | price src | tps | uptime | ✓ |
|---|---|---|---|---|---|---|---|---|---|
| Vultr | 256k | $0.10 | $0.20 | — | via modelsdev | — | — |
sorted by blended price ((3·input + output) / 4 per 1M) · ✓ = the provider's own catalog confirms the offer · "via …" prices are what the aggregator routing the offer charges, not the provider's own list price
source aliases
- llmstats
qwen3.8-flash-next