Model comparison
GLM-5 vs GLM-5.2
Head-to-head evidence from 24 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Sibling matchup inside the GLM-5 family.
Public leaderboard positions: GLM-5 #28 (Supported); GLM-5.2 #37 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GLM-5 and GLM-5.2 share 24 comparable benchmark results. 4 of 8 categories are comparable. 25 results are unique to GLM-5; 19 to GLM-5.2.
Updated July 23, 2026- Shared results
- 24
- GLM-5 only
- 25
- GLM-5.2 only
- 19
- Comparable categories
- 4 / 8
GLM-5 makes more sense if knowledge is the priority or you want the cheaper token bill, while GLM-5.2 is the cleaner fit if mathematics is the priority or you need the larger 1M context window.
Confidence note. This is a partial-evidence comparison with 24 shared benchmark results across 7 evidence categories; 4 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
GLM-5 and GLM-5.2 sit in the same GLM-5 family. This page is less about two unrelated model lineages and more about how the siblings trade off on benchmark shape, token costs, and practical limits like context window.
GLM-5 has the cleaner BenchAlign overall profile here, landing at 66.06 versus 63.96. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
GLM-5's sharpest advantage is in knowledge, where it averages 66.4 against 59.6. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 56.2% to 81%. GLM-5.2 does hit back in mathematics, so the answer changes if that is the part of the workload you care about most.
GLM-5.2 is also the more expensive model on tokens at $1.40 input / $4.40 output per 1M tokens, versus $1.00 input / $3.20 output per 1M tokens for GLM-5. GLM-5.2 is the reasoning model in the pair, while GLM-5 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. GLM-5.2 gives you the larger context window at 1M, compared with 200K for GLM-5.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | GLM-5 | Δ | GLM-5.2 |
|---|---|---|---|
| Math | GLM-556.3 | Margin→ 39.6 | GLM-5.295.9 |
| Agentic | GLM-556.2 | Margin→ 24.8 | GLM-5.281.0 |
| Knowledge | GLM-566.4 | Margin← 6.8 | GLM-5.259.6 |
| Coding | GLM-566.3 | Margin← 4.2 | GLM-5.262.1 |
| Reasoning | GLM-560.8 | MarginNo overlap | GLM-5.2Not measured |
| Multilingual | GLM-583.1 | MarginNo overlap | GLM-5.2Not measured |
| Inst. Following | GLM-592.6 | MarginNo overlap | GLM-5.2Not measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 56.2%B 81%Winner: GLM-5.2Δ 24.8Terminal-Bench 2.0: GLM-5 scored 56.2%; GLM-5.2 scored 81%. GLM-5.2 wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 55.1%B 62.1%Winner: GLM-5.2Δ 7SWE-bench Pro: GLM-5 scored 55.1%; GLM-5.2 scored 62.1%. GLM-5.2 wins this benchmark. - Source ↗
HMMT Feb 2026
MathA 86.4%B 92.5%Winner: GLM-5.2Δ 6.1HMMT Feb 2026: GLM-5 scored 86.4%; GLM-5.2 scored 92.5%. GLM-5.2 wins this benchmark. - Source ↗
GPQA
KnowledgeA 86%B 91.2%Winner: GLM-5.2Δ 5.2GPQA: GLM-5 scored 86%; GLM-5.2 scored 91.2%. GLM-5.2 wins this benchmark. - Source ↗
HLE
KnowledgeA 50.4%B 54.7%Winner: GLM-5.2Δ 4.3HLE: GLM-5 scored 50.4%; GLM-5.2 scored 54.7%. GLM-5.2 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GLM-5 | GLM-5.2 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GLM-5$1 input / $3.2 output | GLM-5.2$1.4 input / $4.4 output | GLM-5 has the lower combined listed price. |
| Generation speedtokens per second | GLM-574 tok/s | GLM-5.2Not available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GLM-51.64 s | GLM-5.2Not available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GLM-5200K | GLM-5.21M | GLM-5.2 lists the larger context window. |
Benchmark Deep Dive
AgenticGLM-5.2 wins25 benchmarks
| Benchmark | GLM-5 | GLM-5.2 | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 56.2% | 81% | GLM-5.2 leads |
| Claw-EvalSource | 57.7% | — | Not comparable |
| QwenClawBenchSource | 54.1% | — | Not comparable |
| τ³-bench resultsSource | 65.6% | — | Not comparable |
| DeepPlanningSource | 14.6% | — | Not comparable |
| ToolathlonSource | 38% | 48.2% | GLM-5.2 leads |
| MCP AtlasSource | 31.1% | 76.8% | GLM-5.2 leads |
| MCP-TasksSource | 60.8% | — | Not comparable |
| WideResearchSource | 69.8% | — | Not comparable |
| τ²-bench resultsSource | 98.2% | 99.1% | GLM-5.2 leads |
| CyberGymSource | 43.2% | — | Not comparable |
| APEX-Agents-AASource | 14.5% | 33.7% | GLM-5.2 leads |
| Gert LabsSource | 50.99% | — | Not comparable |
| AA Agentic IndexSource | — | 43.1% | Not comparable |
| GDPval-AASource | — | 50.7% | Not comparable |
| GDPval-AASource | — | 1514 | Not comparable |
| ResearchClawBenchSource | — | 20.7% | Not comparable |
| AA BriefcaseSource | — | 1260 | Not comparable |
| AA AutomationBenchSource | — | 27.8% | Not comparable |
| AA EnterpriseOps-GymSource | — | 42.7% | Not comparable |
| AA Harvey LABSource | — | 91.0% | Not comparable |
| AA ITBenchSource | — | 42.7% | Not comparable |
| AA Tau3 BankingSource | — | 26.8% | Not comparable |
| terminalBenchHardSource | — | 50.8% | Not comparable |
| aaTerminalBench21Source | — | 77.9% | Not comparable |
CodingGLM-5 wins12 benchmarks
| Benchmark | GLM-5 | GLM-5.2 | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 77.8% | — | Not comparable |
| SWE-bench Verified*Source | 72.8% | — | Not comparable |
| SWE-bench ProSource | 55.1% | 62.1% | GLM-5.2 leads |
| SWE MultilingualSource | 73.3% | — | Not comparable |
| SWE-RebenchSource | 62.8% | — | Not comparable |
| React Native EvalsSource | 74.8% | — | Not comparable |
| AA-SciCodeSource | 46.2% | 50.5% | GLM-5.2 leads |
| NL2RepoSource | — | 48.9% | Not comparable |
| Terminal-Bench 2.0Source | — | 81.0% | Not comparable |
| ProgramBenchSource | — | 63.7% | Not comparable |
| cursorBench32Source | — | 55.0% | Not comparable |
| AA Coding IndexSource | — | 68.8% | Not comparable |
Reasoning4 benchmarks
KnowledgeGLM-5 wins14 benchmarks
| Benchmark | GLM-5 | GLM-5.2 | Result |
|---|---|---|---|
| GPQASource | 86% | 91.2% | GLM-5.2 leads |
| GPQA-DSource | 86.0% | 91.2% | GLM-5.2 leads |
| SuperGPQASource | 66.8% | — | Not comparable |
| MMLU-ProSource | 85.7% | — | Not comparable |
| MMLU-Pro (Arcee)Source | 85.8% | — | Not comparable |
| HLESource | 50.4% | 54.7% | GLM-5.2 leads |
| Artificial Analysis Intelligence IndexSource | 39.5% | 51.1% | GLM-5.2 leads |
| AA-GPQA DiamondSource | 82.0% | 89.5% | GLM-5.2 leads |
| AA-HLESource | 27.2% | 40.1% | GLM-5.2 leads |
| AA-Omniscience IndexSource | 2.0% | 4.0% | GLM-5.2 leads |
| AA-Omniscience AccuracySource | 26.9% | 25.1% | GLM-5 leads |
| AA-Omniscience Hallucination RateSource | 34.0% | 28.1% | GLM-5.2 leads |
| HLE w/o toolsSource | — | 40.5% | Not comparable |
| AA Openness IndexSource | — | 44.4% | Not comparable |
MathGLM-5.2 wins8 benchmarks
| Benchmark | GLM-5 | GLM-5.2 | Result |
|---|---|---|---|
| AIME26Source | 95.8% | 99.2% | GLM-5.2 leads |
| AIME25 (Arcee)Source | 93.3% | — | Not comparable |
| HMMT Feb 2025Source | 97.5% | — | Not comparable |
| HMMT Nov 2025Source | 96.9% | 94.4% | GLM-5 leads |
| HMMT Feb 2026Source | 86.4% | 92.5% | GLM-5.2 leads |
| MMAnswerBenchSource | 82.5% | 91.0% | GLM-5.2 leads |
| FrontierMath v2 (Tiers 1-3)Source | 16.434% | — | Not comparable |
| FrontierMath v2 (Tier 4)Source | 2.100% | — | Not comparable |
Multilingual2 benchmarks
Multimodal1 benchmarks
| Benchmark | GLM-5 | GLM-5.2 | Result |
|---|---|---|---|
| Design Arena WebsiteSource | 1278 | 1340 | GLM-5.2 leads |
Frequently Asked Questions (5)
Which is better, GLM-5 or GLM-5.2?
GLM-5 and GLM-5.2 are sibling variants in the GLM-5 family, so the right pick depends on whether you value the better benchmark line, cheaper tokens, or the larger context window. GLM-5 is ahead on BenchLM's BenchAlign leaderboard 66.06 to 63.96.
Which is better for knowledge tasks, GLM-5 or GLM-5.2?
GLM-5 has the edge for knowledge tasks in this comparison, averaging 66.4 versus 59.6. Inside this category, AA-HLE is the benchmark that creates the most daylight between them.
Which is better for coding, GLM-5 or GLM-5.2?
GLM-5 has the edge for coding in this comparison, averaging 66.3 versus 62.1. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
Which is better for math, GLM-5 or GLM-5.2?
GLM-5.2 has the edge for math in this comparison, averaging 95.9 versus 56.3. Inside this category, MMAnswerBench is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, GLM-5 or GLM-5.2?
GLM-5.2 has the edge for agentic tasks in this comparison, averaging 81 versus 56.2. Inside this category, MCP Atlas is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.