Coding work
Code generation, repair, and software-engineering tasks
GLM-5.2
GLM-5.2 has the higher public coding point estimate, 61 to 59.6, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Updated November 21, 2026. Rank says DeepSeek V4 Pro is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
DeepSeek V4 Pro has the higher public score estimate, 61.6 versus 58.8, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 20 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
DeepSeek V4 Pro: $1.32 input / $3.96 output
GLM-5.2: $1.40 input / $4.40 output
DeepSeek V4 Pro: 1M
GLM-5.2: 1M
DeepSeek V4 Pro: August 13, 2026
GLM-5.2: June 16, 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-5.2
GLM-5.2 has the higher public coding point estimate, 61 to 59.6, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
1K fresh input + 500 output tokens
DeepSeek V4 Pro
DeepSeek V4 Pro has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
DeepSeek V4 Pro
DeepSeek V4 Pro has the lower estimated token cost for this stated workload. GLM-5.2 has no published cached-input rate, so cached tokens use its listed input rate.
50K fresh input + 3K output tokens
DeepSeek V4 Pro
DeepSeek V4 Pro 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
No clear pick
The like-for-like agentic result is a practical tie on the public lane (within 0.5 points).
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
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 v6.0
GLM-5.2 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.
2 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 18.0SWE-bench ProCoding
Normalized gap 6.7FrontierMath v2 (Tiers 1-3)Math
Normalized gap 5.4HMMT Feb 2026Math
Normalized gap 2.7FrontierMath v2 (Tier 4)Math
Normalized gap 2.4Each row shows the public-lane category score for both models: the BenchAlign v6.0 lane in every category, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence. Directional and not-comparable rows remain visible, but they never receive a winner.
| Category | DeepSeek V4 Pro | GLM-5.2 | Basis | Reading |
|---|---|---|---|---|
| Agentic | 60.0Supported · #55/182 | 60.4Supported · #53/182 | Like-for-likeBenchAlign v6.0 lane · 14 vs 9 public rows | Practical tie |
| Coding | 59.6Supported · #56/180 | 61.0Supported · #49/180 | Like-for-likeBenchAlign v6.0 lane · 15 vs 11 public rows | GLM-5.2 leads · intervals overlap |
| Reasoning | 64.6Supported · #32/161 | 52.4Supported · #68/161 | Like-for-likeBenchAlign v6.0 lane · 4 vs 1 public rows | DeepSeek V4 Pro leads · intervals overlap |
| Instruction following | 56.6Supported · #47/143 | 54.9Supported · #51/143 | Like-for-likeBenchAlign v6.0 lane · 0 vs 0 public rows | DeepSeek V4 Pro leads · intervals overlap |
| Math | 59.4Supported · #34/125 | 57.0Supported · #45/125 | Like-for-likeBenchAlign v6.0 lane · 6 vs 6 public rows | DeepSeek V4 Pro leads · intervals overlap |
| Multimodal | 60.7Estimated · #54/119 | 60.3Estimated · #56/119 | Directional onlyBenchAlign v6.0 lane · 0 vs 0 public rows | Directional only |
| Knowledge | 59.7Supported · #46/158 | 55.7Estimated · #60/158 | Directional onlyBenchAlign v6.0 lane · 7 vs 6 public rows | Directional only |
| Multilingual | 57.3Estimated · #31/88 | Not ranked | Not comparableBenchAlign v6.0 lane · 0 vs 0 public rows | Not comparable |
Ranks count the models scored in each category’s BenchAlign v6.0 lane, so denominators differ by category. 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
DeepSeek V4 Pro has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
DeepSeek V4 Pro has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
DeepSeek V4 Pro has the lower modeled cost
GLM-5.2 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 21, 2026.
ADeepSeek V4 ProBGLM-5.2
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 DeepSeek V4 Pro 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.
DeepSeek V4 Pro
GLM-5.2
1M
DeepSeek V4 Pro
deepseek-v4-pro
DeepSeek models and pricingGLM-5.2
Not sourced
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
DeepSeek V4 Pro
$0.044 per 1M cached input tokens
DeepSeek: Models & PricingGLM-5.2
Not published
DeepSeek V4 Pro
GLM-5.2
DeepSeek V4 Pro
GLM-5.2
DeepSeek V4 Pro
Generally Available · DeepSeek API
DeepSeek models and pricing, V4 Pro continuation footnoteGLM-5.2
Not sourced
DeepSeek V4 Pro
Reasoning
GLM-5.2
Reasoning
DeepSeek V4 Pro
Open Weight
GLM-5.2
Open Weight
DeepSeek V4 Pro
Open Weight
GLM-5.2
Open Weight
DeepSeek V4 Pro
2026-08-13
GLM-5.2
2026-06-16
DeepSeek V4 Pro has the higher public score estimate, 61.6 versus 58.8, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
GLM-5.2 has the higher public coding point estimate, 61 to 59.6, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
The like-for-like agentic tasks row is a practical tie on the public lane, 60 against 60.4, inside the 0.5-point band BenchLM treats as level.
For the stated presets, chat costs $0.0033 on DeepSeek V4 Pro and $0.0036 on GLM-5.2; repository review costs $0.07788 and $0.0832; the cache-heavy agent loop costs $0.0748 and $0.352. GLM-5.2 has no published cached-input rate, so cached tokens use its listed input rate.
Both models list the same context window, 1M.
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.
Gert Labs
Shared sourceDeepSeek V4 Pro leads this result
Terminal-Bench 4.1
Not directly comparable
Finch
Not directly comparable
Terminal-Bench 2.0
Not directly comparable
Terminal-Bench 2.1
DeepSeek V4 Pro leads this result
BrowseComp
Not directly comparable
HLE w/ tools
DeepSeek V4 Pro leads this result
MCP Atlas
GLM-5.2 leads this result
Toolathlon
DeepSeek V4 Pro leads this result
CyberGym
Not directly comparable
Toolathlon-Verified
Not directly comparable
Agents' Last Exam
Not directly comparable
AutomationBench
Not directly comparable
Terminal-Bench 2.1 (Vals)
GLM-5.2 leads this result
Terminal-Bench 3.0
Not directly comparable
ResearchClawBench
Not directly comparable
MazeBench
Not directly comparable
LiveCodeBench Pass@1-COT
Not directly comparable
Codeforces
Not directly comparable
SWE-bench Verified
Not directly comparable
SWE-bench Pro
GLM-5.2 leads this result
SWE Multilingual
Not directly comparable
Terminal-Bench 2.0
Not directly comparable
Vibe Code Bench
Not directly comparable
Terminal-Bench 2.1
DeepSeek V4 Pro leads this result
NL2Repo
DeepSeek V4 Pro leads this result
DeepSWE
Not directly comparable
DSBench-FullStack
Not directly comparable
DSBench-Hard
Not directly comparable
OpenHarmony Bench v1.0
Shared sourceDeepSeek V4 Pro leads this result
LiveCodeBench (Vals)
DeepSeek V4 Pro leads this result
SWE-bench (Vals)
DeepSeek V4 Pro leads this result
ProgramBench
Not directly comparable
CursorBench 3.2
Not directly comparable
PostTrainBench v1.1
Not directly comparable
PostTrainBench
Not directly comparable
PostTrainBench v1
Not directly comparable
MRCR 1M
Not directly comparable
CorpusQA 1M
Not directly comparable
ARC-AGI-1
Not directly comparable
ARC-AGI-2
Not directly comparable
CritPt
Not directly comparable
MMLU-Pro
Not directly comparable
Chinese-SimpleQA
Not directly comparable
GPQA
GLM-5.2 leads this result
GPQA-D
GLM-5.2 leads this result
HLE
DeepSeek V4 Pro leads this result
GPQA Diamond (Vals)
DeepSeek V4 Pro leads this result
MMLU-Pro (Vals)
DeepSeek V4 Pro leads this result
HLE w/o tools
Not directly comparable
HMMT Feb 2026
DeepSeek V4 Pro leads this result
IMOAnswerBench
Not directly comparable
Apex
Not directly comparable
Apex Shortlist
Not directly comparable
FrontierMath v2 (Tiers 1-3)
Shared sourceDeepSeek V4 Pro leads this result
FrontierMath v2 (Tier 4)
Shared sourceGLM-5.2 leads this result
AIME26
Not directly comparable
HMMT Nov 2025
Not directly comparable
MMAnswerBench
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 21, 2026