GPT-5.6 Terra vs GLM 5.3: price, benchmarks and speed

Side by side

	GPT-5.6 Terra	GLM 5.3
Lab	OpenAI	Z.AI
Listed	Jul 9, 2026	Aug 18, 2026
Input per 1M tokens	$3.00	$0.12
Output per 1M tokens	$18.00	$5.40
Cached input per 1M	$0.30	$0.11
Blended (3:1) per 1M	$6.75	$1.44
Context window	1.1M	1M
Max output	128K	944K
Knowledge cutoff	2026-02-16	-
Intelligence index	32.2	31.7
Coding index	76.7	74.8
Reasoning	Yes	Yes
Reads images	Yes	No
Tool use	Yes	Yes
Structured output	Yes	Yes

Every benchmark both are scored on

Each model's best score per benchmark, with its source. Scores from different sources or settings are not always comparable; each links to where it was published.

Benchmark	GPT-5.6 Terra	GLM 5.3	Leader
AIME	53.3%Epoch AI	91.1%Epoch AI	GLM 5.3
APEX-Agents	58.2%Epoch AI	56.6%Epoch AI	GPT-5.6 Terra
Artificial Analysis Agentic Index	43.2Artificial Analysis and OpenRouter	53.1Artificial Analysis and OpenRouter	GLM 5.3
Artificial Analysis Coding Index	76.7Artificial Analysis and OpenRouter	74.8Artificial Analysis and OpenRouter	GPT-5.6 Terra
Artificial Analysis Intelligence Index	42.3Artificial Analysis and OpenRouter	31.7Artificial Analysis and OpenRouter	GPT-5.6 Terra
Chess Puzzles	47%Epoch AI	37%Epoch AI	GPT-5.6 Terra
DeepSWE	69.6%Epoch AI	69%Epoch AI	GPT-5.6 Terra
DTBench	93.3%Epoch AI	87.7%Epoch AI	GPT-5.6 Terra
FrontierCode	41.3Epoch AI	40.1Epoch AI	GPT-5.6 Terra
FrontierMath Tier 4 (v2)	70.7%Epoch AI	29.3%Epoch AI	GPT-5.6 Terra
FrontierMath Tiers 1-3 (v2)	86%Epoch AI	68.8%Epoch AI	GPT-5.6 Terra
GPQA Diamond	88.4%Artificial Analysis and OpenRouter	85.4%Artificial Analysis and OpenRouter	GPT-5.6 Terra
LMArena (Coding)	1485 EloLMArena	1497 EloLMArena	GLM 5.3
LMArena (Overall)	1448 EloLMArena	1474 EloLMArena	GLM 5.3
LMArena: Creative Writing	1413 EloLMArena	1459 EloLMArena	GLM 5.3
LMArena: Hard Prompts	1469 EloLMArena	1490 EloLMArena	GLM 5.3
LMArena: Longer Query	1453 EloLMArena	1483 EloLMArena	GLM 5.3
LMArena: Math	1477 EloLMArena	1501 EloLMArena	GLM 5.3
LMArena: Multi-Turn	1455 EloLMArena	1470 EloLMArena	GLM 5.3
LMCA	55Epoch AI	55.5Epoch AI	GLM 5.3
Mystery Game Puzzles	10%Epoch AI	33%Epoch AI	GLM 5.3
ProofBench	74%Epoch AI	49%Epoch AI	GPT-5.6 Terra
SciCode	55%Epoch AI	59%Epoch AI	GLM 5.3
SimpleQA Verified	43.2%Epoch AI	41%Epoch AI	GPT-5.6 Terra
tau-bench (Airline)	72.3%Artificial Analysis and OpenRouter	77.3%Artificial Analysis and OpenRouter	GLM 5.3
WebDev Arena	1521 EloEpoch AI	1614 EloEpoch AI	GLM 5.3
WeirdML	78.3%Epoch AI	75.4%Epoch AI	GPT-5.6 Terra

More comparisons

Where these figures come from

Prices are GenMagic's own, what the studio and the API charge, recomputed from each provider's price list every few minutes. The indices are the Artificial Analysis indices, and every benchmark score links to its source, re-read daily. Measured speed is GenMagic's own generation records, in aggregate. See OpenAI models, Z.AI models, every LLM's price and our sources.