Model comparison
Claude Sonnet 5 vs GLM-5
Head-to-head evidence from 15 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Claude Sonnet 5 #29 (Estimated); GLM-5 #28 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Claude Sonnet 5 and GLM-5 share 15 comparable benchmark results. 3 of 8 categories are comparable. 21 results are unique to Claude Sonnet 5; 34 to GLM-5.
Updated July 23, 2026- Shared results
- 15
- Claude Sonnet 5 only
- 21
- GLM-5 only
- 34
- Comparable categories
- 3 / 8
Pick GLM-5 if you want the stronger benchmark profile. Claude Sonnet 5 only becomes the better choice if agentic is the priority or you need the larger 1M context window.
Confidence note. This is a partial-evidence comparison with 15 shared benchmark results across 5 evidence categories; 3 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 has the cleaner BenchAlign overall profile here, landing at 66.06 versus 65.32. 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 57.4. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 80.4% to 56.2%. Claude Sonnet 5 does hit back in agentic, so the answer changes if that is the part of the workload you care about most.
Claude Sonnet 5 is also the more expensive model on tokens at $2.00 input / $10.00 output per 1M tokens, versus $1.00 input / $3.20 output per 1M tokens for GLM-5. That is roughly 3.1x on output cost alone. Claude Sonnet 5 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. Claude Sonnet 5 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 | Claude Sonnet 5 | Δ | GLM-5 |
|---|---|---|---|
| Agentic | Claude Sonnet 581.9 | Margin← 25.7 | GLM-556.2 |
| Coding | Claude Sonnet 576.7 | Margin← 10.4 | GLM-566.3 |
| Knowledge | Claude Sonnet 557.4 | Margin→ 9.0 | GLM-566.4 |
| Reasoning | Claude Sonnet 5Not measured | MarginNo overlap | GLM-560.8 |
| Math | Claude Sonnet 5Not measured | MarginNo overlap | GLM-556.3 |
| Multilingual | Claude Sonnet 5Not measured | MarginNo overlap | GLM-583.1 |
| Multimodal | Claude Sonnet 588.3 | MarginNo overlap | GLM-5Not measured |
| Inst. Following | Claude Sonnet 5Not measured | MarginNo overlap | GLM-592.6 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 80.4%B 56.2%Winner: Claude Sonnet 5Δ 24.2Terminal-Bench 2.0: Claude Sonnet 5 scored 80.4%; GLM-5 scored 56.2%. Claude Sonnet 5 wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 63.2%B 55.1%Winner: Claude Sonnet 5Δ 8.1SWE-bench Pro: Claude Sonnet 5 scored 63.2%; GLM-5 scored 55.1%. Claude Sonnet 5 wins this benchmark. - Source ↗
SWE-bench Verified
CodingA 85.2%B 77.8%Winner: Claude Sonnet 5Δ 7.4SWE-bench Verified: Claude Sonnet 5 scored 85.2%; GLM-5 scored 77.8%. Claude Sonnet 5 wins this benchmark. - Source ↗
HLE
KnowledgeA 57.4%B 50.4%Winner: Claude Sonnet 5Δ 7HLE: Claude Sonnet 5 scored 57.4%; GLM-5 scored 50.4%. Claude Sonnet 5 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Claude Sonnet 5 | GLM-5 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Claude Sonnet 5$2 input / $10 output | GLM-5$1 input / $3.2 output | GLM-5 has the lower combined listed price. |
| Generation speedtokens per second | Claude Sonnet 5Not available | GLM-574 tok/s | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Claude Sonnet 5Not available | GLM-51.64 s | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Claude Sonnet 51M | GLM-5200K | Claude Sonnet 5 lists the larger context window. |
Benchmark Deep Dive
AgenticClaude Sonnet 5 wins25 benchmarks
| Benchmark | Claude Sonnet 5 | GLM-5 | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 80.4% | 56.2% | Claude Sonnet 5 leads |
| BrowseCompSource | 84.7% | — | Not comparable |
| HLE w/ toolsSource | 57.4% | — | Not comparable |
| OSWorld-VerifiedSource | 81.2% | — | Not comparable |
| GDPval-AASource | 1607 | — | Not comparable |
| AA Agentic IndexSource | 46.7% | — | Not comparable |
| GDPval-AASource | 55.4% | — | Not comparable |
| AA BriefcaseSource | 1388 | — | Not comparable |
| AA AutomationBenchSource | 39.2% | — | Not comparable |
| AA EnterpriseOps-GymSource | 44.7% | — | Not comparable |
| AA Harvey LABSource | 90.1% | — | Not comparable |
| AA Tau3 BankingSource | 28.2% | — | Not comparable |
| aaTerminalBench21Source | 80.5% | — | Not comparable |
| 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% | Not comparable |
| MCP AtlasSource | — | 31.1% | Not comparable |
| MCP-TasksSource | — | 60.8% | Not comparable |
| WideResearchSource | — | 69.8% | Not comparable |
| τ²-bench resultsSource | — | 98.2% | Not comparable |
| CyberGymSource | — | 43.2% | Not comparable |
| APEX-Agents-AASource | — | 14.5% | Not comparable |
| Gert LabsSource | — | 50.99% | Not comparable |
CodingClaude Sonnet 5 wins12 benchmarks
| Benchmark | Claude Sonnet 5 | GLM-5 | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 85.2% | 77.8% | Claude Sonnet 5 leads |
| SWE-bench ProSource | 63.2% | 55.1% | Claude Sonnet 5 leads |
| SWE MultilingualSource | 78.3% | 73.3% | Claude Sonnet 5 leads |
| SWE MultimodalSource | 28.1% | — | Not comparable |
| Terminal-Bench 2.0Source | 80.4% | — | Not comparable |
| FrontierCode 1.1 MainSource | 42.7% | — | Not comparable |
| cursorBench32Source | 61.5% | — | Not comparable |
| AA Coding IndexSource | 71.5% | — | Not comparable |
| AA-SciCodeSource | 53.6% | 46.2% | Claude Sonnet 5 leads |
| SWE-bench Verified*Source | — | 72.8% | Not comparable |
| SWE-RebenchSource | — | 62.8% | Not comparable |
| React Native EvalsSource | — | 74.8% | Not comparable |
Reasoning4 benchmarks
KnowledgeGLM-5 wins13 benchmarks
| Benchmark | Claude Sonnet 5 | GLM-5 | Result |
|---|---|---|---|
| HLESource | 57.4% | 50.4% | Claude Sonnet 5 leads |
| HLE w/o toolsSource | 43.2% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 53.4% | 39.5% | Claude Sonnet 5 leads |
| AA-GPQA DiamondSource | 91.1% | 82.0% | Claude Sonnet 5 leads |
| AA-HLESource | 39.6% | 27.2% | Claude Sonnet 5 leads |
| AA-Omniscience IndexSource | 15.3% | 2.0% | Claude Sonnet 5 leads |
| AA-Omniscience AccuracySource | 38.3% | 26.9% | Claude Sonnet 5 leads |
| AA-Omniscience Hallucination RateSource | 37.3% | 34.0% | GLM-5 leads |
| GPQASource | — | 86% | Not comparable |
| GPQA-DSource | — | 86.0% | Not comparable |
| SuperGPQASource | — | 66.8% | Not comparable |
| MMLU-ProSource | — | 85.7% | Not comparable |
| MMLU-Pro (Arcee)Source | — | 85.8% | Not comparable |
Math8 benchmarks
| Benchmark | Claude Sonnet 5 | GLM-5 | Result |
|---|---|---|---|
| AIME26Source | — | 95.8% | Not comparable |
| AIME25 (Arcee)Source | — | 93.3% | Not comparable |
| HMMT Feb 2025Source | — | 97.5% | Not comparable |
| HMMT Nov 2025Source | — | 96.9% | Not comparable |
| HMMT Feb 2026Source | — | 86.4% | Not comparable |
| MMAnswerBenchSource | — | 82.5% | Not comparable |
| FrontierMath v2 (Tiers 1-3)Source | — | 16.434% | Not comparable |
| FrontierMath v2 (Tier 4)Source | — | 2.100% | Not comparable |
Multilingual2 benchmarks
Multimodal4 benchmarks
Frequently Asked Questions (4)
Which is better, Claude Sonnet 5 or GLM-5?
GLM-5 is ahead on BenchLM's BenchAlign leaderboard, 66.06 to 65.32. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 80.4% and 56.2%.
Which is better for knowledge tasks, Claude Sonnet 5 or GLM-5?
GLM-5 has the edge for knowledge tasks in this comparison, averaging 66.4 versus 57.4. Inside this category, Artificial Analysis Intelligence Index is the benchmark that creates the most daylight between them.
Which is better for coding, Claude Sonnet 5 or GLM-5?
Claude Sonnet 5 has the edge for coding in this comparison, averaging 76.7 versus 66.3. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, Claude Sonnet 5 or GLM-5?
Claude Sonnet 5 has the edge for agentic tasks in this comparison, averaging 81.9 versus 56.2. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Related Comparisons
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.