Updated November 13, 2026. Rank says GLM-5.1 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
GLM-5.1 has the higher public score estimate, 55.47 versus 52.96, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 18 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Claude Opus 4.5: $5 input / $25 output
GLM-5.1: $1.40 input / $4.40 output
Claude Opus 4.5: 200K
GLM-5.1: 203K
Claude Opus 4.5: November 24, 2025
GLM-5.1: April 7, 2026
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.
Code generation, repair, and software-engineering tasks
GLM-5.1
GLM-5.1 has the higher public coding point estimate, 46.2 to 43.6, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Prompts that approach the documented context limit
GLM-5.1
GLM-5.1 has the larger documented context window.
1K fresh input + 500 output tokens
GLM-5.1
GLM-5.1 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
50K fresh input + 3K output tokens
GLM-5.1
GLM-5.1 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Tool use, computer use, and multi-step task completion
Not enough matched evidence
GLM-5.1 is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
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. Claude Opus 4.5 does not fit this workload in one request. GLM-5.1 does not fit this workload in one request. Claude Opus 4.5 has no published cached-input rate, so cached tokens use its listed input rate. GLM-5.1 has no published cached-input rate, so cached tokens use its listed input rate.
Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
Like-for-like · BenchAlign v5.8
GLM-5.1 has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.
We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
4 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
LiveCodeBench (Vals)Coding
Normalized gap 6.4Terminal-Bench 2.0Agentic
Normalized gap 4.2HMMT Feb 2026Math
Normalized gap 2.7FrontierMath v2 (Tiers 1-3)Math
Normalized gap 2.5MMLU-Pro (Vals)Knowledge
Normalized gap 1.3Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, reasoning, multimodal, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
| Category | Claude Opus 4.5 | GLM-5.1 | Basis | Reading |
|---|---|---|---|---|
| Coding | 43.6Supported · #64/162 | 46.2Supported · #55/162 | Like-for-likeBenchAlign v5.8 lane · 8 vs 8 public rows | GLM-5.1 leads · intervals overlap |
| Knowledge | 50.1Supported · #78/180 | 52.0Supported · #69/180 | Like-for-likeBenchAlign v5.8 lane · 8 vs 4 public rows | GLM-5.1 leads · intervals overlap |
| Agentic | 27.3Supported · #109/135 | 44.0Estimated · #63/135 | Directional onlyBenchAlign v5.8 lane · 15 vs 10 public rows | Directional only |
| Reasoning | 41.2Supported · #76/160 | 44.6Estimated · #73/160 | Directional onlyBenchAlign v5.8 lane · 2 vs 0 public rows | Directional only |
| Instruction following | 31.9#139/157 | 93.8#7/157 | Directional onlyProvisional lane · 1 vs 0 weighted rows | Directional only |
| Math | 52.9#10/12 | 55.7#8/12 | Directional onlyProvisional lane · 4 vs 3 weighted rows | Directional only |
| Multimodal | 49.5Estimated · #59/67 | Not ranked | Not comparableBenchAlign v5.8 lane · 18 vs 0 public rows | Not comparable |
| Multilingual | 96.5#2/17 | Not ranked | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, reasoning, multimodal, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
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.
1K fresh input + 500 output tokens
GLM-5.1 has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
GLM-5.1 has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
Claude Opus 4.5 does not fit this workload in one request. GLM-5.1 does not fit this workload in one request. Claude Opus 4.5 has no published cached-input rate, so cached tokens use its listed input rate. GLM-5.1 has no published cached-input rate, so cached tokens use its listed input rate.
Enter a month of tokens to price it at both models’ listed API rates.
Standard listed rates, no batch or volume discounts.
Overall score against output price per 1M tokens, one model per family. Pricing as of November 12, 2026.
Claude Opus 4.5GLM-5.1
Gray dots are the other priced models. The dark step line is the efficiency frontier: for a model under it, another model costs no more and scores at least as high.
See GLM-5.1 on the full price vs performance chartSourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
Maximum documented context; output-token limits may be lower.
Claude Opus 4.5
200K
GLM-5.1
203K
Claude Opus 4.5
Not sourced
GLM-5.1
Not sourced
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Opus 4.5
Not published
GLM-5.1
Not published
Claude Opus 4.5
text, image
Anthropic Claude Opus 4.5 model pageGLM-5.1
Claude Opus 4.5
GLM-5.1
Claude Opus 4.5
Not sourced
GLM-5.1
Not sourced
Claude Opus 4.5
Non-Reasoning
GLM-5.1
Reasoning
Claude Opus 4.5
Proprietary
GLM-5.1
Open Weight
Claude Opus 4.5
Proprietary
GLM-5.1
Open Weight
Claude Opus 4.5
2025-11-24
GLM-5.1
2026-04-07
GLM-5.1 has the higher public score estimate, 55.47 versus 52.96, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
GLM-5.1 has the higher public coding point estimate, 46.2 to 43.6, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
GLM-5.1 scores higher for agentic tasks on the public lane, 44 to 27.3. GLM-5.1 is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
For the stated presets, chat costs $0.0175 on Claude Opus 4.5 and $0.0036 on GLM-5.1; repository review costs $0.325 and $0.0832; the cache-heavy agent loop costs $1.35 and $0.352. Claude Opus 4.5 does not fit this workload in one request. GLM-5.1 does not fit this workload in one request. Claude Opus 4.5 has no published cached-input rate, so cached tokens use its listed input rate. GLM-5.1 has no published cached-input rate, so cached tokens use its listed input rate.
GLM-5.1 has the larger documented context window: 203K, compared with 200K.
Estimates at 50,000 req/day · 1000 tokens/req average.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Terminal-Bench 2.0
GLM-5.1 leads this result
OSWorld-Verified
Not directly comparable
OSWorld
Not directly comparable
Claw-Eval
GLM-5.1 leads this result
QwenClawBench
Not directly comparable
τ³-bench results
GLM-5.1 leads this result
VITA-Bench
Not directly comparable
DeepPlanning
Not directly comparable
Toolathlon
Not directly comparable
MCP Atlas
GLM-5.1 leads this result
MCP-Tasks
Not directly comparable
WideResearch
Not directly comparable
CyberGym
Shared sourceGLM-5.1 leads this result
Gert Labs
Shared sourceClaude Opus 4.5 leads this result
JobBench
Not directly comparable
BrowseComp
Not directly comparable
ResearchClawBench
Not directly comparable
Terminal-Bench 2.1 (Vals)
Not directly comparable
HLE w/ tools
Not directly comparable
SWE-bench Verified
Not directly comparable
LiveCodeBench v6
Not directly comparable
SWE-bench Pro
GLM-5.1 leads this result
SWE Multilingual
Not directly comparable
NL2Repo
Claude Opus 4.5 leads this result
Terminal-Bench 2.0
GLM-5.1 leads this result
LiveCodeBench (Vals)
GLM-5.1 leads this result
PostTrainBench v1
Not directly comparable
SWE-Rebench
Not directly comparable
Vibe Code Bench
Not directly comparable
OpenHarmony Bench v1.0
Not directly comparable
SWE-bench (Vals)
Not directly comparable
MMMU
Not directly comparable
MMMU-Pro
Not directly comparable
RealWorldQA
Not directly comparable
OmniDocBench 1.5
Not directly comparable
Video-MME (with subtitle)
Not directly comparable
Video-MME (w/o subtitle)
Not directly comparable
MathVision
Not directly comparable
We-Math
Not directly comparable
DynaMath
Not directly comparable
SimpleVQA
Not directly comparable
CharXiv
Not directly comparable
CountBench
Not directly comparable
AI2D_TEST
Not directly comparable
ERQA
Not directly comparable
VideoMMMU
Not directly comparable
MLVU (M-Avg)
Not directly comparable
ScreenSpot Pro
Not directly comparable
V*
Not directly comparable
GPQA
Not directly comparable
SuperGPQA
Not directly comparable
MMLU-Pro
Not directly comparable
MMLU-Redux
Not directly comparable
C-Eval
Not directly comparable
HLE
GLM-5.1 leads this result
GPQA Diamond (Vals)
GLM-5.1 leads this result
MMLU-Pro (Vals)
GLM-5.1 leads this result
GPQA-D
Not directly comparable
MMLU-ProX
Not directly comparable
NOVA-63
Not directly comparable
INCLUDE
Not directly comparable
PolyMath
Not directly comparable
MAXIFE
Not directly comparable
AIME26
GLM-5.1 leads this result
HMMT Feb 2025
Not directly comparable
HMMT Nov 2025
GLM-5.1 leads this result
HMMT Feb 2026
Claude Opus 4.5 leads this result
MMAnswerBench
Claude Opus 4.5 leads this result
FrontierMath v2 (Tiers 1-3)
Shared sourceGLM-5.1 leads this result
FrontierMath v2 (Tier 4)
Not directly comparable
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 7,000+ subscribers.
Last updated November 13, 2026
