Skip to content
← Leaderboard

Qwen3.6 35B A3B

Open source
Self-hostable
Free to run
Alibaba (Qwen)
Open license
text
vision
Released 6mo ago
Avg score
62.5
/ 100 · not enough data for the index
Context
262k
Output limit
236k
Input price
$0.10 /M
Output price
$0.95 /M
Parameters
36B · 3B active
Est. VRAM (Q4)
~21.6 GB

Public list price, verified 8h ago · cached input $0.05 /M

Added automatically from the public model catalog. Family and licence details are not curated yet; benchmark scores appear as upstream leaderboards list this model.

Benchmarks

performance

Output SpeedN/A
tok/s

Median output speed in tokens per second over the last 14 days on the model maker's own API, measured nightly with a fixed ~800-token prompt and ~250-token answer. Models not yet probed fall back to a dated manual figure. Higher is faster.

Time to First TokenN/A
ms

Median time from request to first streamed token in milliseconds over the last 14 days on the model maker's own API, using the same nightly probe prompt. Lower is snappier; reasoning models are penalised here because they think before talking.

math

OTIS Mock AIME 2024-2025Fresh
%

AIME-style competition problems written specifically for the OTIS mock contest, then run as an evaluation by Epoch AI. Closer in spirit to the public AIME but with novel problems unlikely to appear in training data.

agentic

Terminal-Bench 2Fresh
%

Long-horizon shell-and-filesystem tasks executed in a sandboxed terminal, scored by whether the agent's final state matches a target state. Tests practical tool-using ability for everyday devops and data-wrangling work; one of the hardest agentic benchmarks today.

reliability

API Success RateN/A
%

Share of nightly probe requests over the last 14 days that streamed a complete answer without an error, timeout or empty response. Needs at least five attempts before a figure is shown.

Reliability monitor

Loading drift signal…

Hosted endpoints

HostInput $/MOutput $/MContextSpeedTTFTUptime 24hQuant
Host 106$0.05$0.70262k140 tok/s0.93 s100.0%fp4
Host 28$0.10$0.90262k130 tok/s0.35 s100.0%fp8
Host 37$0.10$0.95262k——98.9%fp8
Host 29$0.10$0.95262k——100.0%fp8
Host 138$0.10$1.00262k——99.4%unknown
Host 52$0.10$1.00256k——100.0%fp8
Host 115$0.25$1.25262k——100.0%fp8
Host 79$0.25$1.25262k——75.1%fp8
Host 86$0.20$1.27262k——99.2%unknown
Host 43$0.24$1.80262k——98.2%fp8
Anonymised third-party hosts. Sorted by lowest output price. Speed and time to first token are medians from our nightly probe where measured; uptime is the catalog's 24-hour figure.

Compare with...