GPQA Diamond ↗84.52 %
GLM 5.1 · GPQA Diamond · Accuracy ↗
1 more reported result
89.9% · GLM-5.1 · GPQA diamond · Best score (across scorers) · % · Epoch AI · GPQA diamond ↗
Z.ai / MODEL EVIDENCE
GLM-5.1
36 benchmarks · 41 observations · 39 sources · released 2026-04-07
Scores at a glance
36 benchmarks · large dot: GLM-5.1; small dots: closest models where reported
GLM-5.1 · FrontierMath-2025-02-28-Private · Best score (across scorers) · % ↗
GLM-5.1 · FrontierMath-Tier-4-2025-07-01-Private · Best score (across scorers) · % ↗
GLM-5.1 · FrontierMath-Tiers-1-3-v2-Private · Best score (across scorers) · % ↗
1 more reported result
24.91% · GLM-5.1 · FrontierMath-Tiers-1-3-v2-Private · Best score (across scorers) · % · Epoch AI · FrontierMath-Tiers-1-3-v2-Private ↗
GLM-5.1 · OTIS Mock AIME 2024-2025 · Best score (across scorers) · % ↗
SWE-bench Verified ↗74.17%
GLM-5.1 · SWE-Bench verified · Best score (across scorers) · % ↗
1 more reported result
76.4 % · GLM 5.1 (Mini-SWE-agent) · SWE-bench Verified · Score · Vals AI · SWE-bench Verified ↗
GLM-5.1 · SimpleQA Verified · Best score (across scorers) · % ↗
GLM-5.1 · Chess Puzzles · Best score (across scorers) · % ↗
SimpleBench ↗55.1%
GLM-5.1 · SimpleBench · Score (AVG@5) · % ↗
WeirdML (v2) ↗57.1%
GLM-5.1 · WeirdML · Accuracy · % ↗
GLM-5.1 · APEX-Agents · Pass@1 score · % ↗
GLM-5.1 · GBAEval · Overall score · % ↗
CritPt ↗4.57%
GLM-5.1 · CritPt · Accuracy · % ↗
ExploitBench ↗18.1%
GLM-5.1 · ExploitBench · Mean capability · % ↗
1 more reported result
16% · GLM-5.1 · ExploitBench · Mean capability · % · Epoch AI · ExploitBench ↗
ProofBench ↗22.22%
GLM-5.1 · ProofBench · Accuracy · % ↗
SciCode ↗44.79%
GLM-5.1 · SciCode · Score · % ↗
Text Arena (Coding) ↗1508.29 Elo
GLM-5.1 · WebDev Arena · Elo ↗
Epoch Capabilities Index (ECI) ↗149.82 ECI
GLM-5.1 · General ECI · 26 October 2026 fit ↗
Legal Research Bench ↗27.89 %
GLM 5.1 · Legal Research Bench · All-Pass ↗
LegalBench ↗84.39 %
GLM 5.1 · LegalBench · Accuracy ↗
GLM 5.1 · Harvey's Legal Agent Benchmark v1 · Accuracy ↗
CaseLaw v2 ↗51.55 %
GLM 5.1 · CaseLaw · Accuracy ↗
Vals Finance Agent v2 ↗44.79 %
GLM 5.1 · Finance Agent v2 · Accuracy ↗
CorpFin v2 ↗64.45 %
GLM 5.1 · CorpFin · Accuracy ↗
MortgageTax & TaxEval v2 ↗71.19 %
GLM 5.1 · TaxEval · Accuracy ↗
MedCode ↗41.6 %
GLM 5.1 · MedCode · Accuracy ↗
MedScribe ↗72.27 %
GLM 5.1 · MedScribe · Accuracy ↗
AIME 2024–2025 · Vals ↗91.88 %
GLM 5.1 · AIME · Accuracy ↗
MMLU-Pro ↗86.9 %
GLM 5.1 · MMLU Pro · Accuracy ↗
Vibe Code Bench ↗31.46 %
GLM 5.1 (OpenHands) · Vibe Code Bench · original task set ↗
GLM 5.1 · ProgramBench · Accuracy ↗
Code Migration v1.1 ↗25.77 %
GLM 5.1 · Code Migration v1 · Accuracy ↗
LiveCodeBench ↗81.38 %
GLM 5.1 · LiveCodeBench · Accuracy ↗
Public Benefits Bench v1.1 ↗61.84 %
GLM 5.1 · Public Benefits Bench · Accuracy ↗
1 more reported result
57.92 % · GLM 5.1 · Public Benefits Bench v1 · Accuracy · Vals AI · Public Benefits Bench v1 ↗
ALE-Bench ↗887.1 Performance points
glm-5.1 · Average contest performance ↗
Vending-Bench 2 ↗5634.406 USD
GLM-5.1 · End-of-year balance ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
Gemini 3.5 Flash Lite →Google
14 of 23 shared benchmark comparisons
Kimi K2.6 →Kimi
21 of 23 shared benchmark comparisons
Qwen 3.6 Plus →Qwen
15 of 23 shared benchmark comparisons
How similarity is measured
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- Arena leaderboard — WebDev evaluation ↗
- SciCode Benchmark | Artificial Analysis ↗
- Ale Bench — methodology and published results ↗
- APEX-Agents ↗
- Chess Puzzles ↗
- CritPt v1 ↗
- ExploitBench v0.1 ↗
- FrontierMath Tier 4 (v1, old) ↗
- FrontierMath Tiers 1-3 (v1, old) ↗
- FrontierMath Tiers 1-3 (v2) ↗
- GPQA Diamond ↗
- OTIS Mock AIME 2024-2025 ↗
- SimpleQA Verified ↗
- SimpleBench ↗
- SWE-bench Verified ↗
- Vending Bench 2 — methodology and published results ↗
- AI benchmarks & capabilities ↗
- GLM-5.1 — GBA Eval ↗
- WeirdML ↗
- AIME — evaluation methodology and results ↗
- CaseLaw — evaluation methodology and results ↗
- Code Migration v1 — evaluation methodology and results ↗
- CorpFin — evaluation methodology and results ↗
- Finance Agent v2 — evaluation methodology and results ↗
- GPQA Diamond — evaluation methodology and results ↗
- Harvey's Legal Agent Benchmark v1 — evaluation methodology and results ↗
- LiveCodeBench — evaluation methodology and results ↗
- LegalBench — evaluation methodology and results ↗
- Legal Research Bench — evaluation methodology and results ↗
- MedCode — evaluation methodology and results ↗
- MedScribe — evaluation methodology and results ↗
- MMLU Pro — evaluation methodology and results ↗
- ProgramBench — evaluation methodology and results ↗
- ProofBench — evaluation methodology and results ↗
- Public Benefits Bench — evaluation methodology and results ↗
- Public Benefits Bench v1 — evaluation methodology and results ↗
- SWE-bench Verified — evaluation methodology and results ↗
- TaxEval — evaluation methodology and results ↗
- Vibe Code Bench — evaluation methodology and results ↗
Names used in source tables
GLM 5.1 · GLM 5.1 (Mini-SWE-agent) · GLM 5.1 (OpenHands) · GLM-5.1 · glm-5.1