GLM-4.6

GLM-4.6 is a reasoning model from Z.AI. 19 benchmarks count toward its score, in 6 categories.

availableShows if the model has enough results for an index.
IndexOverall score. 50 is the middle.42.2 ±5.2
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.79/s
Input / 1MUS dollars per 1M input tokens.$0.43
Output / 1MUS dollars per 1M output tokens.$1.75
ContextMaximum tokens in one request.205K
EloLMArena rating and rank.1440 (#66)

50 is the middle of the board. The range shows the doubt in the index.

35,061 votes. Elo shows what people prefer. It does not change the score.

CapabilitiesScore per category. 50 is the middle.

50 is the middle
AgenticMulti-step tasks with tools.
48.1
CodingCode writing and repair.
47.1
ReasoningLogic problems and puzzles.
32.4
MultimodalTasks with images and text.
N/A
KnowledgeFacts and expert knowledge.
40.4
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
26.4
MathMath problems.
45.6

Results

19 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result on the index scale.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
AIMEMath92.7%56.916 Apr 2026Vals AI
MGSMMultilingual89.7%9 Jan 2026Vals AI
MMLU ProKnowledge82.2%50.01 Sept 2026Vals AI
LiveCodeBenchCoding81.0%58.01 Sept 2026Vals AI
τ²-Bench Tool-Agent-User EvaluationAgentic76.9%54.0Victor Barres et al.
GPQA DiamondKnowledge74.5%47.01 Sept 2026Vals AI
Artificial Analysis GPQA DiamondKnowledge63.2%33.3Artificial Analysis
SWE-bench VerifiedCoding61.8%47.1mini-SWE-agent1 Sept 2026SWE-bench team
SWE-bench VerifiedCoding55.4%42.0mini-SWE-agent26 Feb 2026SWE-bench team
Terminal-Bench 1.0Agentic42.5%47.612 Jan 2026Vals AI
Artificial Analysis IFBenchInstruction36.7%26.4Artificial Analysis
Terminal-Bench 2.0Agentic28.1%42.74 Jun 2026Vals AI
Artificial Analysis Long Context ReasoningReasoning26.3%26.5Artificial Analysis
Artificial Analysis Omniscience AccuracyKnowledge21.4%40.3Artificial Analysis
Artificial Analysis Intelligence IndexKnowledge14.9%41.1Artificial Analysis
Artificial Analysis Humanity's Last ExamKnowledge5.5%30.5Artificial Analysis
IOI v1Coding4.3%42.49 Aug 2026Vals AI
FrontierMath-2025-02-28-PrivateMath3.8%34.2Epoch AI
Vibe Code Bench v1.1Coding3.1%43.5OpenHands21 Sept 2026Vals AI
FrontierMath-Tier-4-2025-07-01-PrivateMath2.1%45.8Epoch AI
Critical Physics TasksReasoning0.0%38.4Artificial Analysis

19 benchmarks count, from 20 of 21 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authorsOpenRouter, collected directlyNo licence statedVals AI, collected directlyNo licence stated. Read from the public leaderboard and credited to Vals AISWE-bench team, collected directlyNo licence stated. The repository publishes submission records for reproducibility and transparency and asks that SWE-bench be citedEpoch AI, collected directlyCC BY — free to use and redistribute with attribution

Same level, lower price

Qwen3.8-Flash-Next66.4 · Freedots3-note Preview65.5 · FreeApodex 1.1 Mini59.1 · Free

More from Z.AI

GLM-5.369.6GLM-5.3-Flash65.6GLM-5.262.7GLM-5.157.8GLM-552.2