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-4.7?

112 SI-IQ · 90% interval 107–118
Rank 56 of 80 ranked models · Plausible rank range 39–67

GLM-4.7 is a model from Z.ai (Zhipu AI), released on Dec 22, 2025. Its SI-IQ is 112 (90% interval 107–118), estimated from 5 benchmark results by 2 independent evaluators.

Facts

Developer: Z.ai (Zhipu AI)
Released: Dec 22, 2025
Access: Open weights (restricted licence)
Benchmarks used: 5 results from 2 evaluators
API price: $0.60 input / $2.20 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	21.0%	113	Epoch AI	`glm-4.7`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
OTIS Mock AIME 2024–2025	Math	83.3%	110	Epoch AI	`glm-4.7`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond	Knowledge	83.3%	112	Epoch AI	`glm-4.7`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond (OpenRouter run)	Knowledge	83.6%	117	OpenRouter	`z-ai/glm-4.7-20251222` Z.AI · first-party provider (1 of 9 rows)	Oct 18, 2026	OpenRouter benchmark datasets · data file
SimpleQA Verified	Knowledge	32.2%	111	Epoch AI	`glm-4.7`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
τ²-bench Airline (OpenRouter run)	Agents	70.4%	121	OpenRouter	`z-ai/glm-4.7-20251222` Z.AI · first-party provider (1 of 9 rows)	Oct 18, 2026	OpenRouter benchmark datasets · data file

Human preference (Arena)

On the Arena leaderboard, where people vote between two anonymous answers, GLM-4.7 has a rating of 1,441 (1,435–1,447) from 12,253 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
o4-miniOpenAI	112	GLM-4.7 vs o4-mini
Qwen3-235B-A22B-Thinking (Jul 2025)Alibaba	111	GLM-4.7 vs Qwen3-235B-A22B-Thinking (Jul 2025)
Claude Sonnet 4.6Anthropic	113	GLM-4.7 vs Claude Sonnet 4.6
Qwen3.5 397B-A17BAlibaba	114	GLM-4.7 vs Qwen3.5 397B-A17B
InklingThinking Machines	114	GLM-4.7 vs Inkling

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); API list prices via LiteLLM's price table (MIT); each price links to the developer's pricing page; Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter..