Model comparison
GLM-5 vs GLM-5.1
Head-to-head evidence from 28 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-5.1 #18 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GLM-5 and GLM-5.1 share 28 comparable benchmark results. 4 of 8 categories are comparable. 21 results are unique to GLM-5; 8 to GLM-5.1.
Updated July 23, 2026- Shared results
- 28
- GLM-5 only
- 21
- GLM-5.1 only
- 8
- Comparable categories
- 4 / 8
GLM-5 makes more sense if knowledge is the priority or you want the cheaper token bill, while GLM-5.1 is the cleaner fit if agentic is the priority or you need the larger 203K context window.
Confidence note. This is a partial-evidence comparison with 28 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-5.1 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-5.1 has the cleaner BenchAlign overall profile here, landing at 67.74 versus 66.06. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
GLM-5.1's sharpest advantage is in agentic, where it averages 65.4 against 56.2. The single biggest benchmark swing on the page is FrontierMath v2 (Tiers 1-3), 16.434% to 33.448%. GLM-5 does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
GLM-5.1 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-5.1 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-5.1 gives you the larger context window at 203K, 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-5.1 |
|---|---|---|---|
| Knowledge | GLM-566.4 | Margin← 14.1 | GLM-5.152.3 |
| Agentic | GLM-556.2 | Margin→ 9.2 | GLM-5.165.4 |
| Math | GLM-556.3 | Margin→ 5.7 | GLM-5.162.0 |
| Coding | GLM-566.3 | Margin← 5.0 | GLM-5.161.3 |
| Reasoning | GLM-560.8 | MarginNo overlap | GLM-5.1Not measured |
| Multilingual | GLM-583.1 | MarginNo overlap | GLM-5.1Not measured |
| Inst. Following | GLM-592.6 | MarginNo overlap | GLM-5.1Not measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
FrontierMath v2 (Tiers 1-3)
MathA 16.434%B 33.448%Winner: GLM-5.1Δ 17FrontierMath v2 (Tiers 1-3): GLM-5 scored 16.434%; GLM-5.1 scored 33.448%. GLM-5.1 wins this benchmark. - Source ↗
FrontierMath v2 (Tier 4)
MathA 2.100%B 12.500%Winner: GLM-5.1Δ 10.4FrontierMath v2 (Tier 4): GLM-5 scored 2.100%; GLM-5.1 scored 12.500%. GLM-5.1 wins this benchmark. - Source ↗
Terminal-Bench 2.0
AgenticA 56.2%B 63.5%Winner: GLM-5.1Δ 7.3Terminal-Bench 2.0: GLM-5 scored 56.2%; GLM-5.1 scored 63.5%. GLM-5.1 wins this benchmark. - Source ↗
HMMT Feb 2026
MathA 86.4%B 82.6%Winner: GLM-5Δ 3.8HMMT Feb 2026: GLM-5 scored 86.4%; GLM-5.1 scored 82.6%. GLM-5 wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 55.1%B 58.4%Winner: GLM-5.1Δ 3.3SWE-bench Pro: GLM-5 scored 55.1%; GLM-5.1 scored 58.4%. GLM-5.1 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GLM-5 | GLM-5.1 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GLM-5$1 input / $3.2 output | GLM-5.1$1.4 input / $4.4 output | GLM-5 has the lower combined listed price. |
| Generation speedtokens per second | GLM-574 tok/s | GLM-5.1Not available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GLM-51.64 s | GLM-5.1Not available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GLM-5200K | GLM-5.1203K | GLM-5.1 lists the larger context window. |
Benchmark Deep Dive
AgenticGLM-5.1 wins18 benchmarks
| Benchmark | GLM-5 | GLM-5.1 | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 56.2% | 63.5% | GLM-5.1 leads |
| Claw-EvalSource | 57.7% | 62.3% | GLM-5.1 leads |
| QwenClawBenchSource | 54.1% | — | Not comparable |
| τ³-bench resultsSource | 65.6% | 70.6% | GLM-5.1 leads |
| DeepPlanningSource | 14.6% | — | Not comparable |
| ToolathlonSource | 38% | — | Not comparable |
| MCP AtlasSource | 31.1% | 71.8% | GLM-5.1 leads |
| MCP-TasksSource | 60.8% | — | Not comparable |
| WideResearchSource | 69.8% | — | Not comparable |
| τ²-bench resultsSource | 98.2% | 97.7% | GLM-5 leads |
| CyberGymSource | 43.2% | 68.7% | GLM-5.1 leads |
| APEX-Agents-AASource | 14.5% | — | Not comparable |
| Gert LabsSource | 50.99% | 60.11% | GLM-5.1 leads |
| BrowseCompSource | — | 68% | Not comparable |
| AA Agentic IndexSource | — | 29.9% | Not comparable |
| GDPval-AASource | — | 37.8% | Not comparable |
| GDPval-AASource | — | 1257 | Not comparable |
| ResearchClawBenchSource | — | 18.2% | Not comparable |
CodingGLM-5 wins10 benchmarks
| Benchmark | GLM-5 | GLM-5.1 | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 77.8% | — | Not comparable |
| SWE-bench Verified*Source | 72.8% | — | Not comparable |
| SWE-bench ProSource | 55.1% | 58.4% | GLM-5.1 leads |
| SWE MultilingualSource | 73.3% | — | Not comparable |
| SWE-RebenchSource | 62.8% | 62.7% | GLM-5 leads |
| React Native EvalsSource | 74.8% | — | Not comparable |
| AA-SciCodeSource | 46.2% | 43.8% | GLM-5 leads |
| NL2RepoSource | — | 42.7% | Not comparable |
| Vibe Code BenchSource | — | 31.46% | Not comparable |
| AA Coding IndexSource | — | 55.8% | Not comparable |
Reasoning4 benchmarks
KnowledgeGLM-5 wins12 benchmarks
| Benchmark | GLM-5 | GLM-5.1 | Result |
|---|---|---|---|
| GPQASource | 86% | — | Not comparable |
| GPQA-DSource | 86.0% | 86.2% | GLM-5.1 leads |
| SuperGPQASource | 66.8% | — | Not comparable |
| MMLU-ProSource | 85.7% | — | Not comparable |
| MMLU-Pro (Arcee)Source | 85.8% | — | Not comparable |
| HLESource | 50.4% | 52.3% | GLM-5.1 leads |
| Artificial Analysis Intelligence IndexSource | 39.5% | 40.2% | GLM-5.1 leads |
| AA-GPQA DiamondSource | 82.0% | 86.8% | GLM-5.1 leads |
| AA-HLESource | 27.2% | 28.0% | GLM-5.1 leads |
| AA-Omniscience IndexSource | 2.0% | 1.9% | GLM-5 leads |
| AA-Omniscience AccuracySource | 26.9% | 24.2% | GLM-5 leads |
| AA-Omniscience Hallucination RateSource | 34.0% | 29.4% | GLM-5.1 leads |
MathGLM-5.1 wins8 benchmarks
| Benchmark | GLM-5 | GLM-5.1 | Result |
|---|---|---|---|
| AIME26Source | 95.8% | 95.3% | GLM-5 leads |
| AIME25 (Arcee)Source | 93.3% | — | Not comparable |
| HMMT Feb 2025Source | 97.5% | — | Not comparable |
| HMMT Nov 2025Source | 96.9% | 94.0% | GLM-5 leads |
| HMMT Feb 2026Source | 86.4% | 82.6% | GLM-5 leads |
| MMAnswerBenchSource | 82.5% | 83.8% | GLM-5.1 leads |
| FrontierMath v2 (Tiers 1-3)Source | 16.434% | 33.448% | GLM-5.1 leads |
| FrontierMath v2 (Tier 4)Source | 2.100% | 12.500% | GLM-5.1 leads |
Multilingual2 benchmarks
Multimodal1 benchmarks
| Benchmark | GLM-5 | GLM-5.1 | Result |
|---|---|---|---|
| Design Arena WebsiteSource | 1278 | 1305 | GLM-5.1 leads |
Frequently Asked Questions (5)
Which is better, GLM-5 or GLM-5.1?
GLM-5 and GLM-5.1 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-5.1 is ahead on BenchLM's BenchAlign leaderboard 67.74 to 66.06.
Which is better for knowledge tasks, GLM-5 or GLM-5.1?
GLM-5 has the edge for knowledge tasks in this comparison, averaging 66.4 versus 52.3. Inside this category, AA-GPQA Diamond is the benchmark that creates the most daylight between them.
Which is better for coding, GLM-5 or GLM-5.1?
GLM-5 has the edge for coding in this comparison, averaging 66.3 versus 61.3. 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-5.1?
GLM-5.1 has the edge for math in this comparison, averaging 62 versus 56.3. Inside this category, FrontierMath v2 (Tiers 1-3) is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, GLM-5 or GLM-5.1?
GLM-5.1 has the edge for agentic tasks in this comparison, averaging 65.4 versus 56.2. Inside this category, MCP Atlas is the benchmark that creates the most daylight between them.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
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.