GLM-4.7

GLM-4.7 is a reasoning model from Z.AI. 28 benchmarks count toward its score, in 6 categories.

availableShows if the model has enough results for an index.
IndexOverall score out of 100.50.2 ±4.6
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.24/s
Input / 1MUS dollars per 1M input tokens.$0.4
Output / 1MUS dollars per 1M output tokens.$1.75
ContextMaximum tokens in one request.205K
EloLMArena rating and rank.1436 (#78)

The index is a score out of 100. The ± range shows how much it can change.

11,893 votes. Elo shows what people prefer. It does not change the score.

CapabilitiesScore per category, out of 100.

Out of 100
AgenticMulti-step tasks with tools.
50.5
CodingCode writing and repair.
52.6
ReasoningLogic problems and puzzles.
43.5
MultimodalTasks with images and text.
N/A
KnowledgeFacts and expert knowledge.
52.5
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
58.0
MathMath problems.
48.7

Results

28 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result as a score out of 100.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
τ²-Bench Tool-Agent-User EvaluationAgentic95.9%67.6Victor Barres et al.
American Invitational Mathematics Examination 2025Math95.7%51.9Mathematical Association of America
AIMEMath93.3%57.216 Apr 2026Vals AI
Artificial Analysis LiveCodeBenchCoding89.4%Artificial Analysis
MGSMMultilingual88.2%9 Jan 2026Vals AI
Artificial Analysis GPQA DiamondKnowledge85.9%56.6Artificial Analysis
Graduate-Level Google-Proof Q&AKnowledge85.7%57.4David Rein et al.
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for CodeCoding84.9%61.5Naman Jain et al.
Massive Multitask Language Understanding ProfessionalKnowledge84.3%53.3Yubo Wang et al.
GPQA diamondKnowledge83.3%55.2Epoch AI
OTIS Mock AIME 2024-2025Math83.3%58.1Epoch AI
MMLU ProKnowledge82.7%50.91 Sept 2026Vals AI
LiveCodeBenchCoding82.2%59.11 Sept 2026Vals AI
GPQA DiamondKnowledge80.0%52.11 Sept 2026Vals AI
Software Engineering Benchmark VerifiedCoding73.8%56.7Carlos E. Jimenez et al.
Artificial Analysis Long Context ReasoningReasoning71.0%57.4Artificial Analysis
SWE-benchCoding69.4%53.21 Sept 2026Vals AI
Artificial Analysis IFBenchInstruction67.9%58.0Artificial Analysis
SWE-RebenchCoding58.7%Nebius
BrowseCompAgentic52.0%43.6OpenAI
Terminal-Bench 1.0Agentic50.0%53.912 Jan 2026Vals AI
Artificial Analysis Coding IndexCoding45.3%50.9Artificial Analysis
Gert Labs Composite Game BenchmarkAgentic40.0%48.0Gert Labs
Terminal-Bench 2.0Agentic38.2%49.94 Jun 2026Vals AI
SimpleQA VerifiedKnowledge32.2%51.4Epoch AI
Artificial Analysis Omniscience AccuracyKnowledge29.3%50.1Artificial Analysis
Artificial Analysis Humanity's Last ExamKnowledge27.4%54.3Artificial Analysis
GDPval-AA normalizedAgentic25.0%54.8Artificial Analysis
Humanity's Last ExamKnowledge24.8%49.8Center for AI Safety et al.
Artificial Analysis Intelligence IndexKnowledge22.2%50.2Artificial Analysis
VITA-BenchAgentic15.5%35.8Meituan LongCat Team
IOI v1Coding7.6%44.29 Aug 2026Vals AI
Chess PuzzlesReasoning6.0%31.3Epoch AI
FrontierMath-2025-02-28-PrivateMath2.4%32.9Epoch AI
Critical Physics TasksReasoning1.7%41.9Artificial Analysis
FrontierMath-Tier-4-2025-07-01-PrivateMath0.0%43.4Epoch AI

28 benchmarks count, from 33 of 36 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 AIEpoch 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