Chat turn cost
1K fresh input + 500 output tokens
Mercury 3
Mercury 3 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
GLM-5.2 vs Mercury 3
Updated October 19, 2026. We do not rank this pair: at least one has no public score. Public scores include evidence status and uncertainty.
Share or export
Decision reading
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. 1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
- Shared results
- 1
- GLM-5.2 only
- 29
- Mercury 3 only
- 7
- Like-for-like categories
- 0 / 8
Supported: GLM-5.2How the comparison works
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.
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Mercury 3
Mercury 3 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.
Confidence: rate-fallback
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
Mercury 3
Mercury 3 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-ratesCoding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Mercury 3 is not ranked on the public lane for coding, so no winner is named for coding.
Confidence: limitedAgentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Mercury 3 is not ranked on the public lane for agentic, so no winner is named for agentic.
Confidence: limitedLong documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
Which one for a specific job
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.
53.7GLM-5.2—Mercury 3
Not comparable · BenchAlign v5.8
The coding row is not comparable on the public lane: at least one model is not measured or not ranked there.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Same basis rules as the category table below
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
29 GLM-5.2 only
1 Shared
7 Mercury 3 only
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.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, 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.
Agentic
Not comparable- GLM-5.2
- 57.4
- Supported · #36/130
- Mercury 3
- Not ranked
- Basis
- BenchAlign v5.8 lane · 8 vs 3 public rows
- Reading
- Not comparable
Coding
Not comparable- GLM-5.2
- 53.7
- Supported · #35/151
- Mercury 3
- Not ranked
- Basis
- BenchAlign v5.8 lane · 9 vs 1 public rows
- Reading
- Not comparable
Reasoning
Not comparable- GLM-5.2
- 78.8
- Unranked · 2 rankable rows
- Mercury 3
- Not ranked
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- GLM-5.2
- Not ranked
- Mercury 3
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Knowledge
Not comparable- GLM-5.2
- 57.9
- Supported · #54/186
- Mercury 3
- Not ranked
- Basis
- BenchAlign v5.8 lane · 6 vs 1 public rows
- Reading
- Not comparable
Multilingual
Not comparable- GLM-5.2
- Not ranked
- Mercury 3
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- GLM-5.2
- 89.9
- #26/148
- Mercury 3
- Not ranked
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Math
Not comparable- GLM-5.2
- 78.4
- #3/12
- Mercury 3
- Not ranked
- Basis
- Provisional lane · 4 vs 0 weighted rows
- Reading
- Not comparable
| Category | GLM-5.2 | Mercury 3 | Basis | Reading |
|---|---|---|---|---|
| Agentic | 57.4Supported · #36/130 | Not ranked | Not comparableBenchAlign v5.8 lane · 8 vs 3 public rows | Not comparable |
| Coding | 53.7Supported · #35/151 | Not ranked | Not comparableBenchAlign v5.8 lane · 9 vs 1 public rows | Not comparable |
| Reasoning | 78.8Unranked · 2 rankable rows | Not ranked | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Multimodal | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Knowledge | 57.9Supported · #54/186 | Not ranked | Not comparableBenchAlign v5.8 lane · 6 vs 1 public rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | 89.9#26/148 | Not ranked | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Math | 78.4#3/12 | Not ranked | Not comparableProvisional lane · 4 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, 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.
Supported evidence per lane · bars run 0–100Methodology
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
- GLM-5.2
- $0.0036
- Fits in one request
- Mercury 3
- $0.00028
- Fits in one request
Mercury 3 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- GLM-5.2
- $0.0832
- Fits in one request
- Mercury 3
- $0.00605
- Fits in one request
Mercury 3 has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- GLM-5.2
- $0.352
- Fits in one request
- Cached input priced at the published list-input rate
- Mercury 3
- $0.0075
- Fits in one request
Mercury 3 has the lower modeled cost
GLM-5.2 has no published cached-input rate, so cached tokens use its listed input rate.
Cached input falls back to the list input rate only where a cached rate is unpublished
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationGLM-5.2Mercury 3
Context window
Maximum documented context; output-token limits may be lower.
GLM-5.2
1M
API model ID
GLM-5.2
Not sourced
Mercury 3
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GLM-5.2
Not published
Mercury 3
$0.01 per 1M cached input tokens
Inception Mercury 3 models page and launch pricingDocumented inputs
GLM-5.2
Not sourced
Mercury 3
Not sourced
Documented outputs
GLM-5.2
Not sourced
Mercury 3
Not sourced
Provider availability
GLM-5.2
Not sourced
Mercury 3
Not sourced
Reasoning profile
GLM-5.2
Reasoning
Mercury 3
Reasoning
Weight access
GLM-5.2
Open Weight
Mercury 3
Proprietary
License
GLM-5.2
Open Weight
Mercury 3
Proprietary
Release date
GLM-5.2
2026-06-16
Mercury 3
2026-10-19
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
- At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
- Workload cost
- Repository review: $0.0832 vs $0.00605. Cache-heavy agent loop: $0.352 vs $0.0075.
- Context tradeoff
- Both models list 1M.
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, GLM-5.2 or Mercury 3?
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, GLM-5.2 or Mercury 3?
Mercury 3 is not ranked on the public lane for coding, so no winner is named for coding.
Which is better for agentic tasks, GLM-5.2 or Mercury 3?
Mercury 3 is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, GLM-5.2 or Mercury 3?
For the stated presets, chat costs $0.0036 on GLM-5.2 and $0.00028 on Mercury 3; repository review costs $0.0832 and $0.00605; the cache-heavy agent loop costs $0.352 and $0.0075. GLM-5.2 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, GLM-5.2 or Mercury 3?
Both models list the same context window, 1M.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence37 rows
Agentic
Terminal-Bench 3.0
GLM-5.24.6%SourceMercury 3—Not directly comparable
Terminal-Bench 2.1
GLM-5.281.0%SourceMercury 3—Not directly comparable
MCP Atlas
GLM-5.276.8%SourceMercury 3—Not directly comparable
Toolathlon
GLM-5.248.2%SourceMercury 3—Not directly comparable
ResearchClawBench
GLM-5.220.7%SourceMercury 3—Not directly comparable
Terminal-Bench 2.1 (Vals)
GLM-5.267.8%SourceMercury 3—Not directly comparable
HLE w/ tools
GLM-5.254.7%SourceMercury 3—Not directly comparable
MazeBench
GLM-5.20%SourceMercury 3—Not directly comparable
τ³-bench results
GLM-5.2—Mercury 330.2%SourceNot directly comparable
BrowseComp+
GLM-5.2—Mercury 355.18%SourceNot directly comparable
DeepSearchQA
GLM-5.2—Mercury 371.3%SourceNot directly comparable
Coding
SWE-bench Pro
GLM-5.262.1%SourceMercury 3—Not directly comparable
NL2Repo
GLM-5.248.9%SourceMercury 3—Not directly comparable
Terminal-Bench 2.1
GLM-5.281.0%SourceMercury 3—Not directly comparable
ProgramBench
GLM-5.263.7%SourceMercury 3—Not directly comparable
CursorBench 3.2
GLM-5.255.0%SourceMercury 3—Not directly comparable
OpenHarmony Bench
GLM-5.258.4%SourceMercury 3—Not directly comparable
LiveCodeBench (Vals)
GLM-5.269.5%SourceMercury 3—Not directly comparable
SWE-bench (Vals)
GLM-5.282.8%SourceMercury 3—Not directly comparable
PostTrainBench v1.1
GLM-5.231.7%SourceMercury 3—Not directly comparable
DeepSWE
GLM-5.2—Mercury 346.3%SourceNot directly comparable
Reasoning
Knowledge
GPQA
GLM-5.291.2%SourceMercury 3—Not directly comparable
GPQA-D
GLM-5.291.2%SourceMercury 389.2%SourceGLM-5.2 leads this result
HLE
GLM-5.240.5%SourceMercury 3—Not directly comparable
HLE w/o tools
GLM-5.240.5%SourceMercury 3—Not directly comparable
GPQA Diamond (Vals)
GLM-5.285.6%SourceMercury 3—Not directly comparable
MMLU-Pro (Vals)
GLM-5.286.7%SourceMercury 3—Not directly comparable
Instruction following
Math
AIME26
GLM-5.299.2%SourceMercury 3—Not directly comparable
HMMT Nov 2025
GLM-5.294.4%SourceMercury 3—Not directly comparable
HMMT Feb 2026
GLM-5.292.5%SourceMercury 3—Not directly comparable
MMAnswerBench
GLM-5.291.0%SourceMercury 3—Not directly comparable
FrontierMath v2 (Tiers 1-3)
GLM-5.259.206%SourceMercury 3—Not directly comparable
FrontierMath v2 (Tier 4)
GLM-5.229.268%SourceMercury 3—Not directly comparable
37 public results · 1 shared
Watch GLM-5.2 vs Mercury 3
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 5,600+ readers.
Last updated October 19, 2026