Zhipu AIChina· released Apr 2026· open weights

GLM 5.1

Name: GLM 5.1
Author: Zhipu AI

Ranked #30, 42.5% behind the frontier on average.

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

Third-party publishedMedium confidence (7+ comparable tests, 3+ Index categories)

Snapshot September 8, 2026

OpenCharts Index

57.5

Ranked #30 (29 to 30) of 36 · 42.5% behind the frontier on average · 13 comparable tests · 3 counting categories

Drop any single test and the Index lands between 54.7 and 60.5, anywhere from #29 to #30. Neighbours inside that range are ties.

Needs more results (2 of 8 so far)

Averaging 64.1 on the 2 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 5.1, in 13 results.

Strongest in coding (63.2) and reasoning (57.7). It trails the frontier most in math, 48.4% behind on average. No comparable results yet in multimodal and long context. Between 40% and 50% behind the best published results, on average. Drop any single test and it would sit anywhere from #29 to #30.

Strongest category

Coding

Writing, fixing and shipping real code, judged by tests or users.

63.2

SWE-bench Verified74.2% · 89% of best
SciCode43.8% · 71% of best
WeirdML57.1% · 62% of best
Code Arena (WebDev)1,508 · 32% win rate vs leader

Mean of 4 of the category's 7 comparable tests. Counts toward the Index.

Best single result

Mock AIME 2024–2025

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

93.3%

93.3% of the best (100.0%) · #29 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Solve an unpublished research-level physics problem to a numeric or symbolic answer checked by an official server.

4.6%

85.8% behind the best published result (32.3%) · #46 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 · 45.0
Agentic1 of 8 tests · needs 4 · mean 77.9
Human preferencesingle-test category, shown beside the Index · 88.2

Every score, with its source

See it at work

What GLM 5.1 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 88.2 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.

1,466

44% expected win rate against the board leader (1,507)
#34 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 5.1 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 5.1

#30·Index 57.5C-

0 : 9

wins · 0 ties · 9 shared

GPT-6 Astra

#1·Index 99.0A+

GPT-6 Astra comes out ahead on 9 of the 9 tests both have taken.

Category means

Reasoning
57.7
99.6
Knowledge
45.0
100.0
Coding
63.2
97.7
Math
51.6
99.8
Agentic
77.9
98.5
Human preference
88.2
—

Shared tests · biggest gaps first

CritPtReasoning
4.6%
31.7%
−84.0
ProofBenchMath
22.2%
99.0%
−76.8
Code Arena (WebDev)Coding
1,508
1,797
−68.1
FrontierMath (Tiers 1–3)Math
36.8%
93.7%
−60.7
SimpleQA VerifiedKnowledge
34.0%
75.6%
−55.0
WeirdMLCoding
57.1%
92.9%
−38.5
SciCodeCoding
43.8%
56.5%
−20.5
GPQA DiamondReasoning
89.9%
95.8%
−8.3
Mock AIME 2024–2025Math
93.3%
100.0%
−6.7

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

Reasoning57.7 · 3/6
Knowledgebeside45.0 · 1/1
Coding63.2 · 4/7
Math51.6 · 3/5
Agentic77.9 · 1/8
Multimodal—
Human preferencebeside88.2 · 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

89.9%

91.7% of the best (95.8%), above chance
61th percentile of 78 · n = 198

Source: Epoch AI — AI Benchmarking Hub

SimpleBenchLeaderboardReasoning

55.1%

67.3% of the best (81.9%)
31th percentile of 46

Source: Epoch AI — AI Benchmarking Hub

CritPtLeaderboardReasoning

4.6%

14.2% of the best (32.3%)
42th percentile of 78

Source: Epoch AI — AI Benchmarking Hub