whatmodel.sh / Qwen3.6 Flash

Qwen3.6 Flash

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Qwen3.6 Flash is a closed-weights language model from Alibaba, released April 2026.

Catalogue identity notes

Comparison-only. Epoch result CSVs list 'qwen3.6-flash' (Alibaba, release date 2026-04-27). Highest published effort per file, as for all Epoch rows.

66.2±1.3#126 of 719 LLMsfrom 7 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Qwen3.6 Flash, out of 828 with a score, then more from Alibaba.

#modelscorewhereRAMreleased
143Grok 4.1 Fast (Reasoning) SpaceXAI (xAI)66±1api $0.28/M2025-11
144o4-mini OpenAI66±1api $1.93/M2025-04
145Qwen3.6 Flash Alibaba66±1api $0.56/M2026-04
146MiMo-V2-Flash (309B-A15B) Xiaomi66±1local~108GB2025-12
147GLM-4.6 Z.ai66±1api $1.00/M +local~58GB2025-09
more from Alibaba
18Qwen3.8 Max (2.4T-A95B) Alibaba78±1api $3.00/M +local~380GB2026-08
34Qwen3.8 Max (0902) Alibaba76±1api $3.00/M2026-09
37Qwen3.8-Flash-Next Alibaba75±1local~59GB2026-08

see all LLMs · find the ones that fit your machine

$ what it's good at

math▁▂▃▅▆▅▄█▄▁▁▁ #142 of 398 * · 61% of its score · 2 tests

Beats Claude Sonnet 4.6, MiMo-V2.5 (310B-A15B), MiniMax-M2.7 here, though they rank higher overall. Trails Olmo 3 32B Think, Olmo 3.1 32B Think, gpt-oss-20b here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
FrontierMath tiers 1–3 v217.2% ✎▂··▁▁▃▄▄█▅▃▃ beats 9/82very hard · avg 1.2%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 50%sharp
OTIS mock AIME 2024–202584.4% ✎▃▃▄▃▃▃▇▇█▃▂▅ beats 124/193very hard · avg 8.5%▇▇▇▇ 11%sharp · at its level · noisy
vision & documents▁▁▃▂▁▃▄▂▆▇█▄ #34 of 147 * · 1.3% of its score · 1 test

Beats MiMo-V2.6-Pro, MiMo-V2.6-Flash (309B-A15B), GPT-5.6 Luna here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
SpaceCast-Bench predictive spatial reasoning (overall, 16 task types)47.7% ✎▃·▅▃▅▃··▅··█ beats 8/11very hard · avg 32%▇ 1.3%blunt · noisy
other tests4 not in a task · 37% of its score
testresultvs the others in its rundifficultycountswhy
GPQA Diamond83.3% ✎▁▁▁▁▂▄▆▄▅▇█▅ beats 136/208hard · avg 40%▇▇▇▇▇▇▇▇▇ 22%sharp · at its level
Chess Puzzles (Epoch)20.0% ✎█▁▁▁▁▂▁▄▂▂▁▁ beats 79/135very hard · avg 5.9%▇▇ 5.1%sharp · noisy
Mystery Game Puzzles (Epoch)12.0% ✎█··▃▃▇▄█▂▃▁▁ beats 18/74very hard · avg 9.4%▇▇ 4.8%sharp · too hard for it · noisy
SimpleQA Verified15.9% ✎▁▁▃▃▃▃▆▆█▃▂▅ beats 9/78very hard · avg 8.0%▇▇ 4.6%at its level

$ where to run it

Through an API

api · Alibaba Cloud Model Studio · $0.56/M · $0.25 in / $1.5 out per 1M tokens · 1M context · www.alibabacloud.com ↗ · price sourceUSD per 1M tokens, Singapore (International), qwen3.6-flash (currently equivalent to qwen3.6-flash-2026-04-16), 0<Token<=256K input tier: input $0.25, output $1.5; the 256K-1M tier ($1/$4) is priced higher. Batch (50%) and context-cache discounts and free quota excluded. Observed 2026-09-25.

$ how the score was worked out · Epoch AI — internal evaluatio… 98%, SpaceCast-Bench: Evaluating P… 1%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
Epoch AI — internal evaluations6▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 98%CC BY 4.0
SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models (arXiv:2610.12402v1)1▇ 1%CC BY 4.0
prior · pull toward the middle▇ 1%
weighted average= 66.2

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json