Zhipu AIChina· released Feb 2026· open weights

GLM 5

Name: GLM 5
Author: Zhipu AI

Provisional: 12 comparable tests so far. Ranked once it reaches 6 across 3 counting categories.

Zhipu AI, China. One of 7 models from this lab on the Index.

Third-party publishedLow confidence (thin coverage)

Snapshot September 8, 2026

OpenCharts Index

51.1

Provisional: not enough comparable tests or counting categories to rank yet · 12 comparable tests · 1 counting categories

Drop any single test and the Index lands between 38.5 and 66.4.

Needs more results (3 of 8 so far)

Averaging 51.1 on the 3 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

GLM 5, in 12 results.

Strongest in reasoning (51.1). Its widest gap is on ARC-AGI-2, 94.9% behind the best published result. No comparable results yet in knowledge, multimodal and long context. Between 40% and 50% behind the best published results, on average.

Strongest category

Reasoning

Hard, novel problems: graduate science, abstract puzzles, expert exams.

51.1

GPQA Diamond87.8% · 89% of best
SimpleBench53.2% · 65% of best
ARC-AGI-144.7% · 45% of best
ARC-AGI-24.9% · 5% of best

Mean of 4 of the category's 6 comparable tests. Counts toward the Index.

Best single result

GPQA Diamond

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

87.8%

88.8% of the best (95.8%), above chance · #39 of 78.

Expert-level science questions are the closest thing to asking a specialist colleague. A model that gets them right can check a technical claim instead of echoing it.

Where it trails

ARC-AGI-2

Infer the hidden rule from a few input and output grid pairs, then apply it to a new grid.

4.9%

94.9% behind the best published result (95.0%) · #45 of 51.

Novel visual puzzles resist memorization, so they measure fluid intelligence rather than recall.

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
Multimodal
Long context

Covered, but not averaged into the Index:

Coding3 of 7 tests · needs 4 · mean 53.5
Math1 of 5 tests · needs 3 · mean 80.0
Agentic3 of 8 tests · needs 4 · mean 56.1
Human preferencesingle-test category, shown beside the Index · 85.9

Every score, with its source

See it at work

What GLM 5 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.

Human preference · mean 85.9 across 1 comparable test · a single-test category, shown beside the Index and never averaged into it

Text ArenaLeaderboard

Answer the same prompt as a rival model; real users vote blind on which answer they prefer.

1,458

43% expected win rate against the board leader (1,507)
#40 of 92

board 2026-09-02

Source: Arena

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

GLM 5 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.

GLM 5

provisional·Index 51.1C-

0 : 7

wins · 0 ties · 7 shared

GPT-6 Astra

#1·Index 99.0A+

GPT-6 Astra comes out ahead on 7 of the 7 tests both have taken.

Category means

Reasoning
51.1
99.6
Knowledge
—
100.0
Coding
53.5
97.7
Math
80.0
99.8
Agentic
56.1
98.5
Human preference
85.9
—

Shared tests · biggest gaps first

ARC-AGI-2Reasoning
4.9%
95.0%
−94.9
Code Arena (WebDev)Coding
1,436
1,797
−77.8
APEX-AgentsAgentic
17.2%
46.7%
−62.2
ARC-AGI-1Reasoning
44.7%
98.5%
−54.6
WeirdMLCoding
48.2%
92.9%
−48.1
Mock AIME 2024–2025Math
80.0%
100.0%
−20.0
GPQA DiamondReasoning
87.8%
95.8%
−11.2

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

Reasoning51.1 · 4/6
Knowledge—
Coding53.5 · 3/7
Math80.0 · 1/5
Agentic56.1 · 3/8
Multimodal—
Human preferencebeside85.9 · 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

87.8%

88.8% of the best (95.8%), above chance
48th percentile of 78 · n = 198

Source: Epoch AI — AI Benchmarking Hub

ARC-AGI-2LeaderboardReasoning

4.9%

5.1% of the best (95.0%)
8th percentile of 51 · n = 120

Source: Epoch AI — AI Benchmarking Hub

ARC-AGI-1LeaderboardReasoning

44.7%

45.4% of the best (98.5%)
4th percentile of 51 · n = 100

Source: Epoch AI — AI Benchmarking Hub