Earlier Qwen multimodal workhorse for million-token agent and document tasks
Specification
most-agreed values
Context
1M
Max output
66K
Released
2026-04-02
Knowledge cutoff
2025-04
Retires
—
Open weights
no
Input
text, image, video
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.50
Output
$3.00
Cache read
$0.10
Cache write
$0.78
Quality
9 benchmarks · 2 sources
Composite
67th
percentile of 334 scored models
Rank
112 / 334
±0.07 sd
Evidence
9 × 2
3 or more benchmarks, from 2 or more sources
Effort range
—
one configuration only
coding46th1/3 bench
reasoning82nd2/4 bench
math71st4/7 bench
knowledge54th1/1 bench
general16th1/1 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3 ±3.8 | default | Epoch AI | 2026-08-07 |
| GPQA diamond | 88.4 ±2.3 | default | Epoch AI | 2026-08-07 |
| FrontierMath-v1 | 38.1 ±2.6 | default · 2 runs | Epoch AI | 2026-05-12 |
| SimpleQA Verified | 44.1 ±1.6 | default | Epoch AI | 2026-08-27 |
| Chess Puzzles | 17.0 ±3.8 | default | Epoch AI | 2026-08-07 |
| SWE-Bench verified | 57.9 ±2.2 | default | Epoch AI | 2026-05-14 |
| FrontierMath-Tiers-1-3-v2 | 38.2 ±2.9 | default | Epoch AI | 2026-08-30 |
| FrontierMath-Tier-4-2025-07-01 | 4.2 ±0.0 | default · 2 runs | Epoch AI | 2026-05-12 |
| LiveBench | 69.0 | default · 23 runs | LiveBench | 2026-06-25 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 3 hosts
Other listings of this model
this page is one of them
The corpus files Qwen3.6 Plus under several keys. This page is the qwen-3-6-plus listing. The full record — every host, every price and every benchmark score — is on the main Qwen3.6 Plus page.
More from Alibaba
most-hosted first