Zhipu AIChina· released Dec 2025· open weights

GLM 4.7

Name: GLM 4.7
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

48.6

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 47.3 and 53.8.

Needs more results (1 of 8 so far)

Averaging 39.4 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

GLM 4.7, in 12 results.

Strongest in reasoning (48.6). Its widest gap is on CritPt, 94.7% behind the best published result. No comparable results yet in multimodal and long context. Between 50% and 60% behind the best published results, on average.

Strongest category

Reasoning

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

48.6

GPQA Diamond83.3% · 82% of best
SimpleBench47.7% · 58% of best
CritPt1.7% · 5% of best

Mean of 3 of the category's 6 comparable tests. Counts toward the Index.

Best single result

Mock AIME 2024–2025

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

83.3%

83.3% of the best (100.0%) · #62 of 78.

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

Where it trails

CritPt

Solve an unpublished research-level physics problem to a numeric or symbolic answer checked by an official server.

1.7%

94.7% behind the best published result (32.3%) · #57 of 78.

Research physics is far past textbook recall. Only a few models produce anything a physicist would accept.

Not measured yet

No comparable result yet in these 2 categories. A blank is a blank, never a zero, and it does not lower the Index.

Multimodal
Long context

Covered, but not averaged into the Index:

Knowledgesingle-test category, shown beside the Index · 42.6
Coding2 of 7 tests · needs 4 · mean 47.5
Math2 of 5 tests · needs 3 · mean 44.7
Agentic3 of 8 tests · needs 4 · mean 36.0
Human preferencesingle-test category, shown beside the Index · 81.4

Every score, with its source

See it at work

What GLM 4.7 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 81.4 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.

1,442

41% expected win rate against the board leader (1,507)
#56 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 4.7 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 4.7

provisional·Index 48.6D

0 : 8

wins · 0 ties · 8 shared

GPT-6 Astra

#1·Index 99.0A+

GPT-6 Astra comes out ahead on 8 of the 8 tests both have taken.

Category means

Reasoning
48.6
99.6
Knowledge
42.6
100.0
Coding
47.5
97.7
Math
44.7
99.8
Agentic
36.0
98.5
Human preference
81.4
—

Shared tests · biggest gaps first

ProofBenchMath
6.0%
99.0%
−93.0
CritPtReasoning
1.7%
31.7%
−92.9
APEX-AgentsAgentic
8.7%
46.7%
−80.1
Code Arena (WebDev)Coding
1,434
1,797
−77.9
SimpleQA VerifiedKnowledge
32.2%
75.6%
−57.4
SciCodeCoding
45.1%
56.5%
−18.2
GPQA DiamondReasoning
83.3%
95.8%
−17.6
Mock AIME 2024–2025Math
83.3%
100.0%
−16.7

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

Reasoning48.6 · 3/6
Knowledgebeside42.6 · 1/1
Coding47.5 · 2/7
Math44.7 · 2/5
Agentic36.0 · 3/8
Multimodal—
Human preferencebeside81.4 · 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

83.3%

82.4% of the best (95.8%), above chance
21th percentile of 78 · n = 198

Source: Epoch AI — AI Benchmarking Hub

SimpleBenchLeaderboardReasoning

47.7%

58.2% of the best (81.9%)
16th percentile of 46

Source: Epoch AI — AI Benchmarking Hub

CritPtLeaderboardReasoning

1.7%

5.3% of the best (32.3%)
26th percentile of 78

Source: Epoch AI — AI Benchmarking Hub