Model

GLM-5.1

OPEN

Zhipu AI / Z.ai (Tsinghua) · GLM-5 family · released Apr 7, 2026

Point release focused on extreme long-horizon agentic engineering; Z.ai's own SWE-bench Pro claim (58.4) briefly topped the public leaderboard, edging out GPT-5.4 and Claude Opus 4.6 on that benchmark at launch.

ReasoningCodingVisionFunction callingTool useAgentic

2199.4

Elo · rank #69

Parameters

744B

Active params

40B (MoE)

Context

200K tokens

Architecture

Mixture-of-Experts, 744B total / 40B active, DeepSeek Sparse Attention (DSA), 200K context, tuned for autonomous long-horizon agent runs (up to 8 hours single-run)

License

MIT

Languages

—

API price (in/out)

$1.4 / $4.4

Modalities

text

Benchmark results

Bar shows position within the tracked field; marker = field best

Agents' Last ExamAgents28.1%#18

best: GPT-6 Astra · 59.3%

AIMEMath95.3%#13

best: GPT-5.2 · 100.0%

Arena EloHuman preference1464#29

best: Claude Fable 5 · 1504

BrowseCompAgents68.0%#27

best: Kimi K3 · 91.2%

CyberGymCoding68.7%#12

best: MiMo-V2.6-Flash · 95.1%

GDPval-AAAgents1260#34

best: Claude Fable 5 · 1932

GPQA DiamondReasoning86.2%#60

best: GPT-6 Astra · 96.0%

Humanity's Last ExamReasoning31.0%#55

best: Claude Opus 5.5 · 67.7%

IFBenchReasoning76.0%#18

best: MiniMax M3 · 83.0%

LiveCodeBenchCoding81.4%#47

best: DeepSeek-V4-Pro (Think Max) · 93.5%

SWE-bench ProCoding58.4%#24

best: Claude Opus 5.5 · 89.9%

SWE-bench VerifiedCoding76.4%#46

best: Claude Opus 5 · 97.0%

Terminal-Bench 2.0Coding63.5%#43

best: DeepSeek-V4.1-Flash · 90.6%

Run it locally

VRAM @ Q4

—

VRAM @ FP16

—

Fits on (Q4)

Multi-node cluster required

Throughput data unavailable.

Quantizations

—

Fine-tune it

Permissive

QLoRA505.9 GB4× H200 141GB

LoRA1584.7 GBbeyond 8× B200

Full fine-tune11941.2 GBbeyond 8× B200

QLoRA SFT on ~10k samples ≈ $20.69 (4× H200 141GB)

Plan a fine-tune →

GLM-5 family

Elo progression across releases

GLM-5Feb 20262036.8 GLM-5.1Apr 20262199.4 GLM-5.2 (High)Jun 20261000.0 GLM-5.2 (Max)Jun 20262399.0 GLM-5.3Aug 20262796.9 GLM-5.3-FlashAug 20262771.9

Resources

HFzai-org/GLM-5.1 DOCShttps://docs.z.ai/guides/llm/glm-5.1 APIAvailable via Zhipu AI / Z.ai (Tsinghua) API

API price $1.4/$4.4 · each benchmark row carries its own source badge (see methodology)