Agentic
Directional only- Claude Sonnet 5
- 81.9
- GLM-5
- 56.2
- Weighted basis
- 3 vs 1 rows
- Reading
- Directional only
Claude Sonnet 5 vs GLM-5
Updated August 14, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
GLM-5 has the higher public score estimate, 65.61 versus 64.78, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
5 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Long documents
Prompts that approach the documented context limit
Claude Sonnet 5
Claude Sonnet 5 has the larger documented context window.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
GLM-5
GLM-5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
GLM-5
GLM-5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
Confidence: limited
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. GLM-5 does not fit this workload in one request. GLM-5 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
14 Claude Sonnet 5 only
5 Shared
31 GLM-5 only
- Shared results
- 5
- Claude Sonnet 5 only
- 14
- GLM-5 only
- 31
- Like-for-like categories
- 0 / 8
3 categories use different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.
Coding
Directional only- Claude Sonnet 5
- 76.7
- GLM-5
- 66.3
- Weighted basis
- 2 vs 3 rows
- Reading
- Directional only
Knowledge
Directional only- Claude Sonnet 5
- 57.4
- GLM-5
- 66.4
- Weighted basis
- 1 vs 4 rows
- Reading
- Directional only
Reasoning
Not comparable- Claude Sonnet 5
- Not measured
- GLM-5
- 60.8
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Math
Not comparable- Claude Sonnet 5
- Not measured
- GLM-5
- 56.3
- Weighted basis
- 0 vs 4 rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Sonnet 5
- Not measured
- GLM-5
- 83.1
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Sonnet 5
- 88.3
- GLM-5
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Sonnet 5
- Not measured
- GLM-5
- 92.6
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
| Category | Claude Sonnet 5 | GLM-5 | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 81.9 | 56.2 | Directional only3 vs 1 rows | Directional only |
| Coding | 76.7 | 66.3 | Directional only2 vs 3 rows | Directional only |
| Knowledge | 57.4 | 66.4 | Directional only1 vs 4 rows | Directional only |
| Reasoning | Not measured | 60.8 | Not comparable0 vs 1 rows | Not comparable |
| Math | Not measured | 56.3 | Not comparable0 vs 4 rows | Not comparable |
| Multilingual | Not measured | 83.1 | Not comparable0 vs 1 rows | Not comparable |
| Multimodal | 88.3 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Instruction following | Not measured | 92.6 | Not comparable0 vs 1 rows | Not comparable |
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
Terminal-Bench 2.0
Agentic
SWE-bench Pro
Coding
SWE-bench Verified
Coding
HLE
Knowledge
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- Claude Sonnet 5
- $0.007
- Fits in one request
- GLM-5
- $0.0026
- Fits in one request
GLM-5 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Sonnet 5
- $0.13
- Fits in one request
- GLM-5
- $0.0596
- Fits in one request
GLM-5 has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Claude Sonnet 5
- $0.18
- Fits in one request
- GLM-5
- $0.252
- Does not fit in one request
- Cached input priced at the published list-input rate
GLM-5 does not fit this workload in one request. GLM-5 has no published cached-input rate, so cached tokens use its listed input rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude Sonnet 5GLM-5
Context window
Maximum documented context; output-token limits may be lower.
Claude Sonnet 5
GLM-5
200K
API model ID
Claude Sonnet 5
claude-sonnet-5
Anthropic model overviewGLM-5
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Sonnet 5
$0.2 per 1M cached input tokens
Claude API pricingGLM-5
Not published
Documented inputs
Claude Sonnet 5
text, image
Anthropic model overviewGLM-5
Not sourced
Documented outputs
Claude Sonnet 5
GLM-5
Not sourced
Provider availability
Claude Sonnet 5
Generally Available · Claude API
Anthropic model overviewGLM-5
Not sourced
Reasoning profile
Claude Sonnet 5
Reasoning
GLM-5
Non-Reasoning
Weight access
Claude Sonnet 5
Proprietary
GLM-5
Open Weight
License
Claude Sonnet 5
Proprietary
GLM-5
Open Weight
Release date
Claude Sonnet 5
2026-06-30
GLM-5
2026-03-01
If you already use one of these models
- Deployment change
- The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
- Quality signal
- GLM-5 has the higher public score estimate, 65.61 versus 64.78, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.13 vs $0.0596. Cache-heavy agent loop: $0.18 vs $0.252.
- Context tradeoff
- Claude Sonnet 5 has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence50 rows
Agentic
Terminal-Bench 3.0
Claude Sonnet 514.6%SourceGLM-5—Not directly comparable
Terminal-Bench 2.0
Claude Sonnet 580.4%SourceGLM-556.2%SourceClaude Sonnet 5 leads this result
BrowseComp
Claude Sonnet 584.7%SourceGLM-5—Not directly comparable
HLE w/ tools
Claude Sonnet 557.4%SourceGLM-5—Not directly comparable
OSWorld-Verified
Claude Sonnet 581.2%SourceGLM-5—Not directly comparable
Claw-Eval
Claude Sonnet 5—GLM-557.7%SourceNot directly comparable
QwenClawBench
Claude Sonnet 5—GLM-554.1%SourceNot directly comparable
τ³-bench results
Claude Sonnet 5—GLM-565.6%SourceNot directly comparable
DeepPlanning
Claude Sonnet 5—GLM-514.6%SourceNot directly comparable
Toolathlon
Claude Sonnet 5—GLM-538%SourceNot directly comparable
MCP Atlas
Claude Sonnet 5—GLM-531.1%SourceNot directly comparable
MCP-Tasks
Claude Sonnet 5—GLM-560.8%SourceNot directly comparable
WideResearch
Claude Sonnet 5—GLM-569.8%SourceNot directly comparable
CyberGym
Claude Sonnet 5—GLM-543.2%SourceNot directly comparable
Gert Labs
Claude Sonnet 5—GLM-550.99%SourceNot directly comparable
Coding
SWE-bench Verified
Claude Sonnet 585.2%SourceGLM-577.8%SourceClaude Sonnet 5 leads this result
SWE-bench Pro
Claude Sonnet 563.2%SourceGLM-555.1%SourceClaude Sonnet 5 leads this result
SWE Multilingual
Claude Sonnet 578.3%SourceGLM-573.3%SourceClaude Sonnet 5 leads this result
SWE Multimodal
Claude Sonnet 528.1%SourceGLM-5—Not directly comparable
Terminal-Bench 2.0
Claude Sonnet 580.4%SourceGLM-5—Not directly comparable
FrontierCode 1.1 Main
Claude Sonnet 542.7%SourceGLM-5—Not directly comparable
cursorBench32
Claude Sonnet 561.5%SourceGLM-5—Not directly comparable
APEX-SWE
Claude Sonnet 546.4%SourceGLM-5—Not directly comparable
EEBench
Claude Sonnet 540.3%SourceGLM-5—Not directly comparable
3DCodeBench
Claude Sonnet 539.2%SourceGLM-5—Not directly comparable
SWE-bench Verified*
Claude Sonnet 5—GLM-572.8%SourceNot directly comparable
SWE-Rebench
Claude Sonnet 5—GLM-562.8%SourceNot directly comparable
React Native Evals
Claude Sonnet 5—GLM-574.8%SourceNot directly comparable
Reasoning
Knowledge
HLE
Claude Sonnet 557.4%SourceGLM-550.4%SourceClaude Sonnet 5 leads this result
HLE w/o tools
Claude Sonnet 543.2%SourceGLM-5—Not directly comparable
GPQA
Claude Sonnet 5—GLM-586%SourceNot directly comparable
GPQA-D
Claude Sonnet 5—GLM-586.0%SourceNot directly comparable
SuperGPQA
Claude Sonnet 5—GLM-566.8%SourceNot directly comparable
MMLU-Pro
Claude Sonnet 5—GLM-585.7%SourceNot directly comparable
MMLU-Pro (Arcee)
Claude Sonnet 5—GLM-585.8%SourceNot directly comparable
Math
AIME26
Claude Sonnet 5—GLM-595.8%SourceNot directly comparable
AIME25 (Arcee)
Claude Sonnet 5—GLM-593.3%SourceNot directly comparable
HMMT Feb 2025
Claude Sonnet 5—GLM-597.5%SourceNot directly comparable
HMMT Nov 2025
Claude Sonnet 5—GLM-596.9%SourceNot directly comparable
HMMT Feb 2026
Claude Sonnet 5—GLM-586.4%SourceNot directly comparable
MMAnswerBench
Claude Sonnet 5—GLM-582.5%SourceNot directly comparable
FrontierMath v2 (Tiers 1-3)
Claude Sonnet 5—GLM-516.434%SourceNot directly comparable
FrontierMath v2 (Tier 4)
Claude Sonnet 5—GLM-52.100%SourceNot directly comparable
Multilingual
Multimodal
Instruction following
IFEval
Claude Sonnet 5—GLM-592.6%SourceNot directly comparable
Frequently asked questions
Which is better, Claude Sonnet 5 or GLM-5?
GLM-5 has the higher public score estimate, 65.61 versus 64.78, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Claude Sonnet 5 or GLM-5?
The current coding averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.
Which is better for agentic tasks, Claude Sonnet 5 or GLM-5?
The current agentic tasks averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.
Which costs less, Claude Sonnet 5 or GLM-5?
For the stated presets, chat costs $0.007 on Claude Sonnet 5 and $0.0026 on GLM-5; repository review costs $0.13 and $0.0596; the cache-heavy agent loop costs $0.18 and $0.252. GLM-5 does not fit this workload in one request. GLM-5 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Claude Sonnet 5 or GLM-5?
Claude Sonnet 5 has the larger documented context window: 1M, compared with 200K.
Related comparisons
Last updated August 14, 2026
Watch Claude Sonnet 5 vs GLM-5
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.