Model comparison
Claude 4 Sonnet vs GLM-5
Head-to-head evidence from 14 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Claude 4 Sonnet #158 (Supported); GLM-5 #28 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Claude 4 Sonnet and GLM-5 share 14 comparable benchmark results. 1 of 8 categories are comparable. 2 results are unique to Claude 4 Sonnet; 35 to GLM-5.
Updated July 20, 2026- Shared results
- 14
- Claude 4 Sonnet only
- 2
- GLM-5 only
- 35
- Comparable categories
- 1 / 8
Pick GLM-5 if you want the stronger benchmark profile. Claude 4 Sonnet only becomes the better choice if coding is the priority.
Confidence note. This is a partial-evidence comparison with 14 shared benchmark results across 6 evidence categories; 1 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 is clearly ahead on the BenchAlign aggregate, 66.06 to 42.79. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Claude 4 Sonnet is also the more expensive model on tokens at $3.00 input / $15.00 output per 1M tokens, versus $1.00 input / $3.20 output per 1M tokens for GLM-5. That is roughly 4.7x on output cost alone.
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 4 Sonnet | Δ | GLM-5 |
|---|---|---|---|
| Coding | Claude 4 Sonnet72.7 | Margin← 6.4 | GLM-566.3 |
| Agentic | Claude 4 SonnetNot measured | MarginNo overlap | GLM-556.2 |
| Reasoning | Claude 4 SonnetNot measured | MarginNo overlap | GLM-560.8 |
| Knowledge | Claude 4 SonnetNot measured | MarginNo overlap | GLM-566.4 |
| Math | Claude 4 SonnetNot measured | MarginNo overlap | GLM-556.3 |
| Multilingual | Claude 4 SonnetNot measured | MarginNo overlap | GLM-583.1 |
| Inst. Following | Claude 4 SonnetNot measured | MarginNo overlap | GLM-592.6 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
SWE-bench Verified
CodingA 72.7%B 77.8%Winner: GLM-5Δ 5.1SWE-bench Verified: Claude 4 Sonnet scored 72.7%; GLM-5 scored 77.8%. GLM-5 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Claude 4 Sonnet | GLM-5 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Claude 4 Sonnet$3 input / $15 output | GLM-5$1 input / $3.2 output | GLM-5 has the lower combined listed price. |
| Generation speedtokens per second | Claude 4 Sonnet40 tok/s | GLM-574 tok/s | GLM-5 has the higher measured throughput. |
| First-answer latencyseconds to first token | Claude 4 Sonnet1.33 s | GLM-51.64 s | Claude 4 Sonnet reaches the first token sooner. |
| Context windowmaximum listed tokens | Claude 4 Sonnet200K | GLM-5200K | Listed context windows are equal. |
Benchmark Deep Dive
Agentic14 benchmarks
| Benchmark | Claude 4 Sonnet | GLM-5 | Result |
|---|---|---|---|
| τ²-bench resultsSource | 52.3% | 98.2% | GLM-5 leads |
| Gert LabsSource | 39.66% | 50.99% | GLM-5 leads |
| JobBenchSource | 18.4% | — | Not comparable |
| Terminal-Bench 2.0Source | — | 56.2% | 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 |
| CyberGymSource | — | 43.2% | Not comparable |
| APEX-Agents-AASource | — | 14.5% | Not comparable |
CodingClaude 4 Sonnet wins7 benchmarks
| Benchmark | Claude 4 Sonnet | GLM-5 | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 72.7% | 77.8% | GLM-5 leads |
| AA-SciCodeSource | 37.3% | 46.2% | GLM-5 leads |
| SWE-bench Verified*Source | — | 72.8% | Not comparable |
| SWE-bench ProSource | — | 55.1% | Not comparable |
| SWE MultilingualSource | — | 73.3% | Not comparable |
| SWE-RebenchSource | — | 62.8% | Not comparable |
| React Native EvalsSource | — | 74.8% | Not comparable |
Reasoning4 benchmarks
Knowledge12 benchmarks
| Benchmark | Claude 4 Sonnet | GLM-5 | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 25.5% | 39.5% | GLM-5 leads |
| AA-GPQA DiamondSource | 68.3% | 82.0% | GLM-5 leads |
| AA-HLESource | 4.0% | 27.2% | GLM-5 leads |
| AA-Omniscience IndexSource | -9.2% | 2.0% | GLM-5 leads |
| AA-Omniscience AccuracySource | 22.4% | 26.9% | GLM-5 leads |
| AA-Omniscience Hallucination RateSource | 40.8% | 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 |
| HLESource | — | 50.4% | Not comparable |
Math8 benchmarks
| Benchmark | Claude 4 Sonnet | 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
Multimodal2 benchmarks
Frequently Asked Questions (2)
Which is better, Claude 4 Sonnet or GLM-5?
GLM-5 is ahead on BenchLM's BenchAlign leaderboard, 66.06 to 42.79. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 72.7% and 77.8%.
Which is better for coding, Claude 4 Sonnet or GLM-5?
Claude 4 Sonnet has the edge for coding in this comparison, averaging 72.7 versus 66.3. Inside this category, AA-SciCode 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.