Qwen3.5-35B-A3B qwen3.5-35b-a3b
qwen · qwen reasoning efficient
#19 overall
- params
- 36B (A3B)
- arch
- moe
- context
- 256k
- license
- apache-2.0 open weights
- released
- Feb 2026
- reasoning
- yes
- downloads/30d
- 2.0M
# why ranked
Overall: #19 — score 35.6 ● medium — one signal missing, weights renormalized
| signal | weight | input (0–100) |
|---|---|---|
| aa_intelligence | 0.50 | 29.3 |
| arena_elo | 0.30 | — |
| bench_composite | 0.20 | 51.4 |
missing signals are dropped and the remaining weights renormalized — never imputed.
# trend
collecting history — trends appear after a few daily runs.
# benchmarks
| benchmark | score | source | date |
|---|---|---|---|
| AA Intelligence Index | 29.3 | Artificial Analysis | — |
| Aa-lcr | 0.6 / 1 | LLM Stats | — |
| Ai2d | 0.9 / 1 | LLM Stats | — |
| Androidworld-sr | 0.7 / 1 | LLM Stats | — |
| Babyvision | 0.4 / 1 | LLM Stats | — |
| Bfcl-v4 | 0.7 / 1 | LLM Stats | — |
| Browsecomp | 0.6 / 1 | LLM Stats | — |
| Browsecomp-zh | 0.7 / 1 | LLM Stats | — |
| C-eval | 0.9 / 1 | LLM Stats | — |
| Cc-ocr | 0.8 / 1 | LLM Stats | — |
| Charxiv-r | 0.8 / 1 | LLM Stats | — |
| Codeforces | 0.8 / 3000 | LLM Stats | — |
| Countbench | 1.0 | LLM Stats | — |
| Deep-planning | 0.2 / 1 | LLM Stats | — |
| Dynamath | 0.8 / 1 | LLM Stats | — |
| Vlmsareblind | 1.0 / 1 | LLM Stats | — |
# where to run
| provider | quant | ctx | $/M in | $/M out | $/M blend | tps | uptime |
|---|---|---|---|---|---|---|---|
| AkashML | fp8 | 256k | $0.14 | $1.00 | $0.35 | — | 100.0% |
| DeepInfra | fp8 | 256k | $0.14 | $1.00 | $0.35 | — | 94.6% |
| Parasail | fp8 | 256k | $0.15 | $1.00 | $0.36 | — | 100.0% |
| Alibaba | unknown | 256k | $0.16 | $1.30 | $0.45 | — | 100.0% |
| WandB | fp8 | 256k | $0.25 | $1.25 | $0.50 | — | 100.0% |
| Venice | unknown | 250k | $0.31 | $1.25 | $0.55 | — | 100.0% |
| NextBit | fp8 | 256k | $0.23 | $1.60 | $0.57 | — | 99.0% |
| AtlasCloud | fp8 | 256k | $0.23 | $1.80 | $0.62 | — | 100.0% |
| SiliconFlow | fp8 | 256k | $0.24 | $1.80 | $0.63 | — | 99.3% |
blended = (3·input + output) / 4 per 1M tokens · cheapest first
source aliases
- llmstats
qwen3.5-35b-a3b- openrouter
qwen/qwen3.5-35b-a3b