GLM-5.2 (high): benchmark scores, price and ranking

GLM-5.2 (high) from Z.ai ranks #109 of 743 LLMs on the LLMs Tiger aggregate benchmark score (51.6), based on 1 benchmark results captured up to 2026-10-13.

Organisation: Z.ai
Type: Open-weight / local model
Open weights: Yes
Released: 2026-06-16 (source: epoch)
Cheapest API price: $0.060 in / $7.00 out per million tokens (via openrouter, observed 2026-10-13T20:47Z)
Aggregate rank: #109 of 743 (score 51.6)

Its cheapest listed input price, $0.060 per million tokens, is lower than that of 89% of the 427 models with a listed price.

GLM-5.2 (high) benchmark results

GLM-5.2 (high) benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
SWE-rebench	62.9%	#2 of 7	SWE-rebench leaderboard	2026-10-13

About GLM-5.2 (high)

GLM-5.2 (high) is an open-weight model that can run on your own hardware from Z.ai. It was released on 2026-06-16, according to Epoch AI. The cheapest API listing we track charges $0.060 per million input tokens and $7.00 per million output tokens, through openrouter. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.

Where GLM-5.2 (high) stands

On our aggregate score, GLM-5.2 (high) is #109 of 743 ranked models, in the top quarter. Its score is 51.6; the scale is centred on 50, so it sits 1.6 points above the typical model. That beats 85% of the ranked field. Among the 5 ranked Z.ai models it is #1. The next one down is glm-5p1 at 51.5.

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so GLM-5.2 (high) costs less than the typical listing. Models that score within 1.5 points or better and cost less: DeepSeek V4 Flash 0731 (max) ($0.016, 53.1), Qwen3.7 Flash ($0.030, 50.5). Similar scores cost more on Qwen3-Coder-30B-A3B-Instruct ($0.070) and Hy3 ($0.083).

Release history

The Z.ai model released before it was GLM-4.5-FP8 on 2025-07-27, which scores 49.6.

Reading these numbers

The 1 score on this page comes from 1 source: SWE-rebench leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. The leaderboard also lists 2 other reasoning-effort settings of this model, which redirect here. This page shows the highest. With 1 results the aggregate rank can move a lot when one new score arrives.

GLM-5.2 (high) is also listed at 2 other reasoning-effort settings; this page shows the highest-effort row, which is the one the leaderboard keeps by default.

Models ranked nearby

#106 Codex + GPT-6 Sol (51.6)
#107 o1-2024-12-17 (51.6)
#108 DeepSeek v4 Pro (max) (51.6)
#110 Hy3-preview (51.6)
#111 LongCat-Flash-Chat (51.6)
#112 Darwin-27B-Opus (51.5)