← comparisons · head to head

Kimi K3 vs GLM-5.2

Kimi K3 scores higher than GLM-5.2 on all 5 public leaderboards that rate both. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, Kimi K3 is at 60.4 and GLM-5.2 at 31.8 (out of 100).

Scores as published by each board; table composed September 24, 2026.

Leaderboard by leaderboard

BoardKimi K3GLM-5.2Higher
LMArena
Elo (community votes)
1,659.61,599.5Kimi K3
LiveBench
global average (0-100)
79.273.2Kimi K3
SimpleBench
AVG@5 % (private set)
60.758.8Kimi K3
Vals AI
Vals Index accuracy % · weighted finance + coding tasks
57.853.1Kimi K3
Artificial Analysis
intelligence index · measured runs only
43.633.7Kimi K3

Raw scores are each board's own scale, so compare within a row, not across rows. Full table: the bench index.

Kimi K3 at a glance

Developer
Moonshot
Status
Live since July 15, 2026

Live — dropped Jul 15 · 2.8T · open weights landed Jul 28 (1.56 TB, MXFP4).

Kimi K3, day one: impressive, expensive, and a little slow

2026-07-16 · Kimi K3 has been live for a day, and the picture forming is more interesting than the launch-night hype. Here's everything we're seeing so far.

Full Kimi K3 tracker →

GLM-5.2 at a glance

Developer
Zhipu AI
Status
Live since June 16, 2026

Live — $0.40/$2.52 per 1M · no longer the current shipped GLM: 5.3 landed Aug 14 and 5.3 Flash Aug 26.

Full GLM-5.2 tracker →

Kimi K3 vs GLM-5.2: quick answers

Which is better, Kimi K3 or GLM-5.2?

It depends on what you measure. Kimi K3 scores higher than GLM-5.2 on all 5 public leaderboards that rate both. Kimi K3's widest lead is on LiveBench. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, Kimi K3 is at 60.4 and GLM-5.2 at 31.8 (out of 100).

Which is newer, Kimi K3 or GLM-5.2?

Kimi K3. It went live on July 15, 2026, 29 days after GLM-5.2 (June 16, 2026).

Who makes Kimi K3 and GLM-5.2?

Kimi K3 is from Moonshot; GLM-5.2 is from Zhipu AI.

Where do these numbers come from?

Each score is the leaderboard's own published figure, read by ArtificialWatch (table composed September 24, 2026). Boards measure different things, so raw scores are only comparable within a row.

More comparisons

GPT-6 Astra vs Claude Fable 5.1GPT-6 Astra vs GPT-5.6GPT-6 Astra vs Claude Opus 5Claude Fable 5.1 vs Claude Fable 5Claude Fable 5.1 vs Claude Opus 5Claude Opus 5 vs GPT-5.6Claude Opus 5 vs Claude Opus 4.8Claude Opus 5 vs Claude Fable 5Claude Opus 5 vs Kimi K3Kimi K3 vs Claude Fable 5Kimi K3 vs GPT-5.6DeepSeek V4 Pro vs GLM-5.2DeepSeek V4 Pro vs Kimi K3
Hear the minute the next one drops.

Watch free: Chrome push the moment a new model answers on a public API, an email about 15 minutes later. Also: the bench index · the wire