Qwen3.5 397B A17B qwen3.5-397b-a17b
qwen · qwen hybrid-reasoning flagship
#31 overall
- params
- 403B (A17B)
- arch
- moe
- context
- 256k
- license
- apache-2.0 open weights
- released
- Feb 2026
- reasoning
- yes
# architecture
- layers
- 60
- d_model
- 4096
- heads
- 32q / 2kv
- head dim
- 256
- experts
- top-10 of 512
- vocab
- 248320
- family
- qwen3_5_moe_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: #31 — score 67.9 ● high — all signals present
| signal | weight | input (0–100) |
|---|---|---|
| aa_intelligence | 0.70 | 66.3 |
| bench_composite | 0.30 | 71.6 |
benchmark panel evidence:
| complete panel | score (0–100) |
|---|---|
| aa-coding-v1 | 76.3 |
| aime-2026-v1 | 57.9 |
| browsecomp-v1 | 80.5 |
Coding: provisional — score 66.2 ● 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 | 66.2 |
| 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 | 48.2 | Artificial Analysis | — |
| AA Intelligence Index | 21.4 | Artificial Analysis | — |
| Aa-lcr | 0.7 / 1 | LLM Stats | — |
| AIME 2026 | 0.9 / 1 | LLM Stats | — |
| Bfcl-v4 | 0.7 / 1 | LLM Stats | — |
| Browsecomp | 0.7 / 1 | LLM Stats | — |
| Browsecomp-zh | 0.7 / 1 | LLM Stats | — |
| C-eval | 0.9 / 1 | LLM Stats | — |
# where to run
| provider | quant | ctx | $/M in | $/M out | $/M cache | price src | tps | uptime | ✓ |
|---|---|---|---|---|---|---|---|---|---|
| Featherless | — | — | — | — | via hfrouter | — | — | ||
| Nebius | — | — | — | — | nebius | — | — | ✓ | |
| Aihubmix | 256k | $0.16 | $0.99 | — | via litellm | — | — | ||
| Alibaba | unknown | 256k | $0.39 | $2.34 | — | via openrouter | — | 99.0% | |
| SiliconFlow | 256k | $0.39 | $2.34 | — | via modelsdev | — | — | ||
| Chutes | fp8 | 256k | $0.45 | $3.00 | — | chutes | — | — | ✓ |
| DeepInfra | fp8 | 256k | $0.45 | $3.00 | — | deepinfra | — | 100.0% | ✓ |
| Parasail | fp8 | 256k | $0.50 | $3.60 | $0.30 | via openrouter | — | 100.0% | |
| AtlasCloud | fp8 | 256k | $0.55 | $3.50 | — | atlascloud | — | 100.0% | ✓ |
| DigitalOcean | unknown | 128k | $0.55 | $3.50 | $0.11 | via openrouter | — | 85.7% | |
| Phala | unknown | 256k | $0.55 | $3.50 | — | phala | — | 100.0% | ✓ |
| GMICloud | fp8 | 256k | $0.60 | $3.60 | — | via openrouter | — | — | |
| Novita | unknown | 256k | $0.60 | $3.60 | — | novita | — | 100.0% | ✓ |
| StreamLake | unknown | 250k | $0.60 | $3.60 | $0.12 | via openrouter | — | 100.0% | |
| Together | 256k | $0.60 | $3.60 | $0.35 | via modelsdev | — | — | ||
| Scaleway | — | $0.68 | $4.10 | — | via hfrouter | 100 | — | ||
| OVHcloud | 256k | $0.71 | $4.25 | — | ovhcloud | 114 | — | ✓ | |
| Venice | unknown | 125k | $0.75 | $4.50 | — | venice | — | 100.0% | ✓ |
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
- aa
qwen3.5-397b-a17b- epoch
Qwen3.5 397B-A17B- openrouter
qwen/qwen3.5-397b-a17b