Qwen3 32B qwen3-32b
qwen · qwen hybrid-reasoning
unranked — no quality signals yet
- params
- 32.8B
- arch
- dense
- context
- 128k
- license
- apache-2.0 open weights
- released
- Apr 2025
- reasoning
- yes
# why ranked
Overall: provisional — score 36.0 ● 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_intelligence | 0.50 | — |
| arena_elo | 0.30 | — |
| bench_composite | 0.20 | 36.0 |
missing signals are dropped and the remaining weights renormalized — never imputed.
Coding: provisional — score 36.4 ● 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 | 0.25 | — |
| aider_polyglot | 0.25 | 36.4 |
| arena_elo_code | 0.15 | — |
| swe_bench_verified | 0.35 | — |
missing signals are dropped and the remaining weights renormalized — never imputed.
# trend
collecting history — trends appear after a few daily runs.
# benchmarks
# where to run
| provider | quant | ctx | $/M in | $/M out | $/M blend | tps | uptime |
|---|---|---|---|---|---|---|---|
| DeepInfra | fp8 | 40k | $0.08 | $0.28 | $0.13 | — | 100.0% |
| Nebius | fp8 | 40k | $0.10 | $0.30 | $0.15 | — | 99.2% |
| Alibaba | unknown | 128k | $0.10 | $0.42 | $0.18 | — | 99.9% |
| SiliconFlow | fp8 | 128k | $0.14 | $0.57 | $0.25 | — | 99.6% |
| Groq | unknown | 128k | $0.29 | $0.59 | $0.36 | — | 100.0% |
blended = (3·input + output) / 4 per 1M tokens · cheapest first
source aliases
- aa
qwen3-32b- aider
Qwen3 32B- arena
Qwen3-32B- openrouter
qwen/qwen3-32b