Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works

How smart is GLM-5.1?

116 SI-IQ · 90% interval 112–120
Rank 48 of 80 ranked models · Plausible rank range 35–64

GLM-5.1 is a model from Z.ai (Zhipu AI), released on Apr 7, 2026. Its SI-IQ is 116 (90% interval 112–120), estimated from 8 benchmark results by 2 evaluators. Its strongest area is Knowledge and its weakest is Math.

Data as of Oct 18, 2026 · method 1.0.0

Facts

Developer: Z.ai (Zhipu AI)
Released: Apr 7, 2026
Access: Open weights (restricted licence)
Benchmarks used: 8 benchmark results from 2 evaluators
API price: $1.40 input / $4.40 output per 1M tokens (developer's price list, Oct 18, 2026)
Context window: 200,000 tokens

Ability by area (SI-IQ, 90% interval)

Every benchmark result we used

Each score is one value exactly as the source published it: for Epoch AI the best of its run settings, for OpenRouter the median hosting provider (the developer's own hosting when it ran the test). “Implied SI-IQ” is the ability that this single result points to; the overall SI-IQ is their precision-weighted average.

Benchmark	Area	Score	Implied SI-IQ	Evaluated by	As listed by the source	Retrieved	Source
Chess Puzzles	Reasoning	20.0%	112	Epoch AI	`glm-5.1`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
FrontierMath Tiers 1–3	Math	36.8%	114	Epoch AI	`glm-5.1`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
OTIS Mock AIME 2024–2025	Math	93.3%	120	Epoch AI	`glm-5.1`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
SWE-bench Verified (Epoch AI run)	Coding	74.2%	120	Epoch AI	`glm-5.1`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond	Knowledge	89.9%	124	Epoch AI	`glm-5.1`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond (OpenRouter run)	Knowledge	81.2%	113	OpenRouter	`z-ai/glm-5.1-20260406` Z.AI · first-party provider (1 of 14 rows)	Oct 18, 2026	OpenRouter benchmark datasets · data file
SimpleQA Verified	Knowledge	34.0%	113	Epoch AI	`glm-5.1`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
τ²-bench Airline (OpenRouter run)	Agents	74.3%	128	OpenRouter	`z-ai/glm-5.1-20260406` Z.AI · first-party provider (1 of 17 rows)	Oct 18, 2026	OpenRouter benchmark datasets · data file

Human preference (Arena)

On the Arena leaderboard, where people vote between two anonymous answers, GLM-5.1 has a rating of 1,465 (1,462–1,469) from 62,889 votes (published Oct 15, 2026). Human preference is a different measure from benchmark ability and is not part of SI-IQ. Arena (Hugging Face)

Models with similar SI-IQ

Model	SI-IQ
o3OpenAI	116	GLM-5.1 vs o3
GPT-5 miniOpenAI	115	GLM-5.1 vs GPT-5 mini
Qwen3.6 27BAlibaba	115	GLM-5.1 vs Qwen3.6 27B
Qwen3.7-PlusAlibaba	115	GLM-5.1 vs Qwen3.7-Plus
Claude Opus 4.5Anthropic	115	GLM-5.1 vs Claude Opus 4.5

Computed with SI-IQ method version 1.0.0. Read the full methodology

Data sources: Arena leaderboard dataset on Hugging Face (CC BY 4.0); Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); LiteLLM, model_prices_and_context_window.json (MIT); Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter (licences and changes).