GLM-5.1

GLM-5.1 is a reasoning model from Z.AI in the GLM-5 family. 39 benchmarks count toward its score, in 6 categories.

availableShows if the model has enough results for an index.
IndexOverall score out of 100.57.8 ±4.1
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.18/s
Input / 1MUS dollars per 1M input tokens.$0.966
Output / 1MUS dollars per 1M output tokens.$3.04
ContextMaximum tokens in one request.205K
EloLMArena rating and rank.1462 (#33)

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

48,901 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.
60.4
CodingCode writing and repair.
58.5
ReasoningLogic problems and puzzles.
51.8
MultimodalTasks with images and text.
N/A
KnowledgeFacts and expert knowledge.
56.8
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
66.5
MathMath problems.
55.8

Results

39 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 EvaluationAgentic97.7%68.9Victor Barres et al.
AIME 2026Math95.3%54.4Qwen
Harvard-MIT Mathematics Tournament November 2025Math94.0%Qwen
OTIS Mock AIME 2024-2025Math93.3%63.7Epoch AI
AIMEMath91.9%56.616 Apr 2026Vals AI
GPQA diamondKnowledge89.9%61.2Epoch AI
MMLU ProKnowledge86.9%57.51 Sept 2026Vals AI
Artificial Analysis GPQA DiamondKnowledge86.8%57.5Artificial Analysis
GPQA DiamondKnowledge86.2%57.8David Rein et al.
GPQA DiamondKnowledge84.5%56.31 Sept 2026Vals AI
MMAnswerBenchMath83.8%Qwen
Harvard-MIT Mathematics Tournament February 2026Math82.6%51.9Qwen
LiveCodeBenchCoding81.4%58.31 Sept 2026Vals AI
SWE-benchCoding76.4%58.81 Sept 2026Vals AI
Artificial Analysis IFBenchInstruction76.3%66.5Artificial Analysis
SWE-Bench verifiedCoding74.2%57.0Epoch AI
Artificial Analysis Long Context ReasoningReasoning73.7%59.2Artificial Analysis
MCP AtlasAgentic71.8%62.2OpenAI
τ³-Bench Tool-Agent-User EvaluationAgentic70.6%55.2Sierra Research
CyberGymAgentic68.7%63.2Zhun Wang et al.
BrowseCompAgentic68.0%57.0OpenAI
SWE-RebenchCoding62.7%Nebius
Claw-EvalAgentic62.3%56.3Bowen Ye et al.
Gert Labs Composite Game BenchmarkAgentic60.1%65.8Gert Labs
SWE-bench ProCoding58.4%60.5Xiang Deng et al.
Terminal-Bench 2.1Agentic56.9%57.621 Sept 2026Vals AI
Artificial Analysis Coding IndexCoding55.8%58.3Artificial Analysis
Terminal-Bench 2.0Agentic53.9%61.24 Jun 2026Vals AI
OpenHarmony Bench v1.0Coding52.3%61.1OpenHarmony Bench authors
Humanity's Last ExamKnowledge52.3%73.1Center for AI Safety et al.
Artificial Analysis SciCodeCoding44.8%55.0Artificial Analysis
NL2RepoCoding42.7%58.4MiniMax
SimpleQA VerifiedKnowledge34.0%53.0Epoch AI
FrontierMath-2025-02-28-PrivateMath33.4%61.8Epoch AI
Vibe Code Bench v1.1Coding31.5%55.3OpenHands21 Sept 2026Vals AI
GDPval-AA normalizedAgentic30.2%58.8Artificial Analysis
Artificial Analysis Humanity's Last ExamKnowledge30.1%57.2Artificial Analysis
Artificial Analysis Intelligence IndexKnowledge26.1%55.0Artificial Analysis
Code MigrationCoding25.8%61.421 Sept 2026Vals AI
Artificial Analysis Agentic IndexAgentic25.2%57.7Artificial Analysis
FrontierMath-Tiers-1-3-v2-PrivateMath24.9%45.5none effortEpoch AI
Artificial Analysis Omniscience AccuracyKnowledge23.7%43.2Artificial Analysis
Chess PuzzlesReasoning19.0%48.1Epoch AI
ResearchClawBenchAgentic18.2%InternScience
FrontierMath-Tier-4-2025-07-01-PrivateMath12.5%57.0Epoch AI
Critical Physics TasksReasoning4.6%48.0Artificial Analysis
ProgramBenchCoding0.0%21 Sept 2026Vals AI

39 benchmarks count, from 42 of 47 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 statedEpoch AI, collected directlyCC BY — free to use and redistribute with attributionVals AI, collected directlyNo licence stated. Read from the public leaderboard and credited to Vals AI

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-552.2GLM-4.750.2