AlibabaChina· released Feb 2026· open weights

Qwen3.5 397B-A17B

Name: Qwen3.5 397B-A17B
Author: Alibaba

Provisional: 6 comparable tests so far. Ranked once it reaches 6 across 3 counting categories.

Alibaba, China. One of 19 models from this lab on the Index.

Third-party publishedLow confidence (thin coverage)

Snapshot September 8, 2026

OpenCharts Index

65.7

Provisional: not enough comparable tests or counting categories to rank yet · 6 comparable tests · 0 counting categories

Drop any single test and the Index lands between 60.2 and 77.6.

Needs more results (1 of 8 so far)

Averaging 33.3 on the 1 it has; the score opens at 4 of 8.

Distance to today's frontier on the hardest tests. Not a measure of intelligence.

What it's known for

Qwen3.5 397B-A17B, in 6 results.

Its widest gap is on Code Arena (WebDev), 81.7% behind the best published result. No comparable results yet in knowledge, agentic and long context. Between 30% and 35% behind the best published results, on average.

Strongest category

No category counts yet: a category counts once it has more than one comparable test and the model has taken at least half of them. The scores it has are below.

Best single result

Mock AIME 2024–2025

Solve competition mathematics problems that have a single exact integer answer.

88.9%

88.9% of the best (100.0%) · #41 of 78.

Olympiad-style problems need long, careful chains of reasoning, and there is no partial credit.

Where it trails

Code Arena (WebDev)

Build a web app from the same prompt as a rival model; real users vote blind on the result.

1,399

81.7 points short of parity with the board leader (1,797) · #56 of 86.

People judging finished apps side by side is the most honest measure of front-end quality.

Not measured yet

No comparable result yet in these 3 categories. A blank is a blank, never a zero, and it does not lower the Index.

Knowledge
Agentic
Long context

Covered, but not averaged into the Index:

Reasoning1 of 6 tests · needs 3 · mean 86.7
Coding1 of 7 tests · needs 4 · mean 18.3
Math2 of 5 tests · needs 3 · mean 61.1
Multimodalsingle-test category, shown beside the Index · 81.3
Human preferencesingle-test category, shown beside the Index · 81.2

Every score, with its source

See it at work

What Qwen3.5 397B-A17B was asked to do, and how it did.

Every test it has taken, by category, with the kind of task it faced, who produced the number and where the result landed against the best published one. The examples are original and illustrative, never items from the datasets themselves.

Reasoning · mean 86.7 across 1 comparable test · not counted toward the Index yet (fewer than half the category's tests)

GPQA DiamondEpoch-run

Answer a PhD-level multiple-choice question in physics, chemistry or biology that a web search will not settle.

86.4%

86.7% of the best (95.8%), above chance
#48 of 78 · n = 198

none

Frontier models cluster in the eighties and nineties; Epoch's standard errors on this test are 2 to 3 points.

Source: Epoch AI (internal runs)

Every result is read against the best published one on its test: percent scores as a share of the best above chance, Arena ratings as the expected win rate against the board leader, open-ended values on a log scale. Sitting a harder exam never lowers a model. Every number links to the publisher that produced it.

Head to head

Qwen3.5 397B-A17B against whoever you pick.

Choose a rival. Every counted test both have taken appears side by side as a share of the best published result on that test, with the category means above. A win is a higher share; a gap under 2 points is a tie, because one item on a 45-problem exam is 2.2 points and publishers' own standard errors are of that order.

Qwen3.5 397B-A17B

provisional·Index 65.7C+

0 : 4

wins · 0 ties · 4 shared

GPT-6 Astra

#1·Index 99.0A+

GPT-6 Astra comes out ahead on 4 of the 4 tests both have taken.

Category means

Reasoning
86.7
99.6
Knowledge
—
100.0
Coding
18.3
97.7
Math
61.1
99.8
Agentic
—
98.5
Multimodal
81.3
—
Human preference
81.2
—

Shared tests · biggest gaps first

Code Arena (WebDev)Coding
1,399
1,797
−81.7
FrontierMath (Tiers 1–3)Math
31.2%
93.7%
−66.7
GPQA DiamondReasoning
86.4%
95.8%
−13.3
Mock AIME 2024–2025Math
88.9%
100.0%
−11.1

Bars are distances to the best published result on each test (percent scores above chance, Arena ratings as win rate against the leader, open-ended values on a log scale). Raw values as the publishers report them.

Open GPT-6 Astra

Scores

Every test, every source

The best published run per benchmark, the raw value as the publisher reports it, who produced the number, how close it comes to the best published result on that test, and where the model sits among every model scored on it. Percent scores are read above chance, Arena ratings as a win rate against the board leader, open-ended values on a log scale. A test with too few models to compare against is shown but not counted.

Category means

Reasoning86.7 · 1/6
Knowledge—
Coding18.3 · 1/7
Math61.1 · 2/5
Agentic—
Multimodalbeside81.3 · 1/1
Human preferencebeside81.2 · 1/1
Long context—

Mean · tests taken of the category's comparable tests. A faded category either rests on fewer than half of them or is a single-test category (marked “beside”), which is shown next to the Index and never averaged into it.

GPQA DiamondEpoch-runReasoning

86.4%

86.7% of the best (95.8%), above chance
39th percentile of 78 · n = 198

none

Source: Epoch AI — AI Benchmarking Hub

Code Arena (WebDev)LeaderboardCoding

1,399

9% expected win rate against the board leader (1,797)
34th percentile of 86

board 2026-09-05

Source: Arena (LMArena) — Leaderboard Dataset

Mock AIME 2024–2025Epoch-runMath

88.9%