Skip to content
Leaderboard / Alibaba (Qwen)

Qwen3.5-Flash

Alibaba (Qwen) CLOSED Proprietary
Verdict

Qwen3.5-Flash is behind the leaders: #224 of 406 by SIscope score. Strongest at chat quality, weaker at coding. Cheaper than 95% of priced models.

SIscope score
42
#224 of 406
Human-vote rank
#160
of 419 · score 1397
Price per 1M tokens, blended
$0.11
$0.065 in · $0.26 out
Context window
1M
1,000,000 tokens

Shape

Each spoke is a category, 0 at the centre, 100 at the edge.

CodingAgentsno data yetReasoningMathChatInstructions

Category scores

Percentiles: 90 means better than about 90% of tested models.

Coding34
Agents & toolsNo data yet–
Reasoning & knowledge46
Math45
Chat quality62
Following instructions60

What goes into each category · Compare with DeepSeek V4.1 Flash

Human-vote score over time

Text arena, recent updates.

139013981405Oct 20: 1396.9 (rank #159)Oct 22: 1397 (rank #159)Oct 28: 1397.1 (rank #160)Oct 20Oct 28

Coding votes over time

WebDev arena, recent updates.

123512431250Oct 16: 1243.8 (rank #132)Oct 18: 1243.7 (rank #133)Oct 19: 1243.7 (rank #137)Oct 22: 1243.7 (rank #138)Oct 23: 1243.7 (rank #139)Oct 27: 1243.8 (rank #139)Oct 28: 1243.7 (rank #140)Oct 16Oct 28

Independent test runs

Run by Epoch AI on the same harness for every model. Bars show the share of questions answered correctly.

GPQA Diamond82%
PhD-level science multiple choice questions
Better than 61% of 333 tested models. Run Aug 7, 2026.
SimpleQA Verified20%
Short factual questions; rewards not making things up
Better than 16% of 100 tested models. Run Aug 27, 2026.
OTIS Mock AIME 2024-2584%
Competition maths problems in the style of AIME
Better than 64% of 313 tested models. Run Aug 7, 2026.
FrontierMath Tiers 1-39%
Very hard, unpublished research-style maths problems
Better than 10% of 122 tested models. Run Aug 28, 2026.

Human-vote arenas

People compare two anonymous answers and pick the better one. Scores work like chess ratings.

ArenaRankScoreRange (95%)VotesUpdated
Text arena
Everyday chat, blind human votes
#160 of 41913971393–140161,776Oct 28, 2026
WebDev arena
Building web apps, blind human votes
#140 of 15212441224–12631,321Oct 28, 2026
Vision arena
Questions about images, blind human votes
Not on this board yet
Agent arena
Real multi-step agent sessions
Not on this board yet

Source: Arena (formerly LMArena) leaderboard dataset, CC BY 4.0. Fetched Nov 4, 2026.

Price

Input
$0.065
per 1M tokens
Output
$0.26
per 1M tokens
Blended
$0.11
3 in : 1 out, per 1M
Context window
1M
max tokens per request
Speed
Coming soon
our own tests

List price from the OpenRouter models API (qwen/qwen3.5-flash-02-23), Nov 4, 2026. Providers can charge differently.