Coding work
Code generation, repair, and software-engineering tasks
GLM-4.7
GLM-4.7 leads on the public coding lane, 39.6 to 35.7, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
GLM-4.7 vs Qwen3.5-122B-A10B
Updated September 27, 2026. Rank says GLM-4.7 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Both of these models will change. Get the price, version and retirement notices for the pair, each with its source. Follow model changes
Share or export
Decision reading
GLM-4.7 has the higher public score estimate, 49.23 versus 40.06, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 5 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
- Shared results
- 5
- GLM-4.7 only
- 12
- Qwen3.5-122B-A10B only
- 10
- Like-for-like categories
- 2 / 8
Supported: GLM-4.7 · Estimated: Qwen3.5-122B-A10BHow 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.
Long documents
Prompts that approach the documented context limit
Qwen3.5-122B-A10B
Qwen3.5-122B-A10B has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
GLM-4.7 and Qwen3.5-122B-A10B are scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limitedChat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-ratesCache-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-4.7 does not fit this workload in one request. GLM-4.7 has no comparable published API token rate. Qwen3.5-122B-A10B has no comparable published API token rate.
Confidence: listed-ratesRepository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
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.
39.6GLM-4.735.7Qwen3.5-122B-A10B
Like-for-like · BenchAlign v5.7
GLM-4.7 leads the like-for-like coding row, although the 90% intervals overlap.
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.
12 GLM-4.7 only
5 Shared
10 Qwen3.5-122B-A10B only
2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
BrowseCompAgentic
Normalized gap 11.8GLM-4.7:52%Qwen3.5-122B-A10B:63.8%Terminal-Bench 2.0Agentic
Normalized gap 8.4GLM-4.7:41%Qwen3.5-122B-A10B:49.4%MMLU-ProKnowledge
Normalized gap 2.4GLM-4.7:84.3%Qwen3.5-122B-A10B:86.7%SWE-bench VerifiedCoding
Normalized gap 1.8GLM-4.7:73.8%Qwen3.5-122B-A10B:72%GPQAKnowledge
Normalized gap 0.9GLM-4.7:85.7%Qwen3.5-122B-A10B:86.6%
Bars run 0–100 on each benchmark’s normalized display scale
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign v5.7 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.
Coding
Like-for-like- GLM-4.7
- 39.6
- Supported · #56/135
- Qwen3.5-122B-A10B
- 35.7
- Supported · #73/135
- Basis
- BenchAlign v5.7 lane · 5 vs 1 public rows
- Reading
- GLM-4.7 leads · intervals overlap
Knowledge
Like-for-like- GLM-4.7
- 40.6
- Supported · #89/158
- Qwen3.5-122B-A10B
- 41.5
- Supported · #86/158
- Basis
- BenchAlign v5.7 lane · 5 vs 3 public rows
- Reading
- Qwen3.5-122B-A10B leads · intervals overlap
Agentic
Directional only- GLM-4.7
- 27.0
- Estimated · #75/105
- Qwen3.5-122B-A10B
- 23.1
- Estimated · #84/105
- Basis
- BenchAlign v5.7 lane · 4 vs 3 public rows
- Reading
- Directional only
Instruction following
Directional only- GLM-4.7
- 81.4
- #51/124
- Qwen3.5-122B-A10B
- 91.6
- #11/124
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Directional only
Reasoning
Not comparable- GLM-4.7
- 70.9
- Unranked · 2 rankable rows
- Qwen3.5-122B-A10B
- 49.8
- Unranked · 3 rankable rows
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- GLM-4.7
- Not ranked
- Qwen3.5-122B-A10B
- 57.0
- #34/50
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- GLM-4.7
- Not ranked
- Qwen3.5-122B-A10B
- 36.8
- #10/12
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Math
Not comparable- GLM-4.7
- 25.8
- Unranked · 2 rankable rows
- Qwen3.5-122B-A10B
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
| Category | GLM-4.7 | Qwen3.5-122B-A10B | Basis | Reading |
|---|---|---|---|---|
| Coding | 39.6Supported · #56/135 | 35.7Supported · #73/135 | Like-for-likeBenchAlign v5.7 lane · 5 vs 1 public rows | GLM-4.7 leads · intervals overlap |
| Knowledge | 40.6Supported · #89/158 | 41.5Supported · #86/158 | Like-for-likeBenchAlign v5.7 lane · 5 vs 3 public rows | Qwen3.5-122B-A10B leads · intervals overlap |
| Agentic | 27.0Estimated · #75/105 | 23.1Estimated · #84/105 | Directional onlyBenchAlign v5.7 lane · 4 vs 3 public rows | Directional only |
| Instruction following | 81.4#51/124 | 91.6#11/124 | Directional onlyProvisional lane · 0 vs 0 weighted rows | Directional only |
| Reasoning | 70.9Unranked · 2 rankable rows | 49.8Unranked · 3 rankable rows | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Multimodal | Not ranked | 57.0#34/50 | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Multilingual | Not ranked | 36.8#10/12 | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Math | 25.8Unranked · 2 rankable rows | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.7) 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-4.7
- Self-hosted; infrastructure cost varies
- Fits in one request
- Qwen3.5-122B-A10B
- Self-hosted; infrastructure cost varies
- Fits in one request
GLM-4.7 has no comparable published API token rate. Qwen3.5-122B-A10B has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- GLM-4.7
- Self-hosted; infrastructure cost varies
- Fits in one request
- Qwen3.5-122B-A10B
- Self-hosted; infrastructure cost varies
- Fits in one request
GLM-4.7 has no comparable published API token rate. Qwen3.5-122B-A10B has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- GLM-4.7
- Self-hosted; infrastructure cost varies
- Does not fit in one request
- Cached-input rate unavailable
- Qwen3.5-122B-A10B
- Self-hosted; infrastructure cost varies
- Fits in one request
- Cached-input rate unavailable
GLM-4.7 does not fit this workload in one request. GLM-4.7 has no comparable published API token rate. Qwen3.5-122B-A10B has no comparable published API token 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-4.7Qwen3.5-122B-A10B
Context window
Maximum documented context; output-token limits may be lower.
GLM-4.7
200K
Qwen3.5-122B-A10B
262K
API model ID
GLM-4.7
Not sourced
Qwen3.5-122B-A10B
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GLM-4.7
No comparable hosted API rate
Qwen3.5-122B-A10B
No comparable hosted API rate
Documented inputs
GLM-4.7
Not sourced
Qwen3.5-122B-A10B
Not sourced
Documented outputs
GLM-4.7
Not sourced
Qwen3.5-122B-A10B
Not sourced
Provider availability
GLM-4.7
Not sourced
Qwen3.5-122B-A10B
Not sourced
Reasoning profile
GLM-4.7
Reasoning
Qwen3.5-122B-A10B
Reasoning
Weight access
GLM-4.7
Open Weight
Qwen3.5-122B-A10B
Open Weight
License
GLM-4.7
Open Weight
Qwen3.5-122B-A10B
Open Weight
Release date
GLM-4.7
2025-10-01
Qwen3.5-122B-A10B
2026-03-04
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-4.7 has the higher public score estimate, 49.23 versus 40.06, but the 90% score intervals overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Qwen3.5-122B-A10B has the larger documented window (262K).
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, GLM-4.7 or Qwen3.5-122B-A10B?
GLM-4.7 has the higher public score estimate, 49.23 versus 40.06, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, GLM-4.7 or Qwen3.5-122B-A10B?
GLM-4.7 leads the public coding lane, 39.6 to 35.7, with Supported evidence for both models, although the 90% intervals overlap.
Which is better for agentic tasks, GLM-4.7 or Qwen3.5-122B-A10B?
GLM-4.7 scores higher for agentic tasks on the public lane, 27 to 23.1. GLM-4.7 and Qwen3.5-122B-A10B are 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.
Which costs less, GLM-4.7 or Qwen3.5-122B-A10B?
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Which has the larger context window, GLM-4.7 or Qwen3.5-122B-A10B?
Qwen3.5-122B-A10B has the larger documented context window: 262K, compared with 200K.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence27 rows
Agentic
Terminal-Bench 2.0
GLM-4.741%SourceQwen3.5-122B-A10B49.4%SourceQwen3.5-122B-A10B leads this result
BrowseComp
GLM-4.752%SourceQwen3.5-122B-A10B63.8%SourceQwen3.5-122B-A10B leads this result
VITA-Bench
GLM-4.715.5%SourceQwen3.5-122B-A10B—Not directly comparable
Gert Labs
GLM-4.739.95%SourceQwen3.5-122B-A10B—Not directly comparable
OSWorld-Verified
GLM-4.7—Qwen3.5-122B-A10B58%SourceNot directly comparable
Coding
SWE-bench Verified
GLM-4.773.8%SourceQwen3.5-122B-A10B72%SourceGLM-4.7 leads this result
LiveCodeBench
GLM-4.784.9%SourceQwen3.5-122B-A10B—Not directly comparable
SWE-Rebench
GLM-4.758.7%SourceQwen3.5-122B-A10B—Not directly comparable
LiveCodeBench (Vals)
GLM-4.782.2%SourceQwen3.5-122B-A10B—Not directly comparable
SWE-bench (Vals)
GLM-4.769.4%SourceQwen3.5-122B-A10B—Not directly comparable
Reasoning
LongBench v2
GLM-4.7—Qwen3.5-122B-A10B60.2%SourceNot directly comparable
Multimodal
MMMU
GLM-4.7—Qwen3.5-122B-A10B83.9%SourceNot directly comparable
MMVU
GLM-4.7—Qwen3.5-122B-A10B74.7%SourceNot directly comparable
MathVision
GLM-4.7—Qwen3.5-122B-A10B86.2%SourceNot directly comparable
CharXiv
GLM-4.7—Qwen3.5-122B-A10B77.2%SourceNot directly comparable
V*
GLM-4.7—Qwen3.5-122B-A10B93.2%SourceNot directly comparable
Knowledge
GPQA
GLM-4.785.7%SourceQwen3.5-122B-A10B86.6%SourceQwen3.5-122B-A10B leads this result
MMLU-Pro
GLM-4.784.3%SourceQwen3.5-122B-A10B86.7%SourceQwen3.5-122B-A10B leads this result
HLE
GLM-4.724.8%SourceQwen3.5-122B-A10B—Not directly comparable
GPQA Diamond (Vals)
GLM-4.780.1%SourceQwen3.5-122B-A10B—Not directly comparable
MMLU-Pro (Vals)
GLM-4.782.7%SourceQwen3.5-122B-A10B—Not directly comparable
SuperGPQA
GLM-4.7—Qwen3.5-122B-A10B67.1%SourceNot directly comparable
Multilingual
MMLU-ProX
GLM-4.7—Qwen3.5-122B-A10B82.2%SourceNot directly comparable
Instruction following
IFEval
GLM-4.7—Qwen3.5-122B-A10B93.4%SourceNot directly comparable
Math
27 public results · 5 shared
Watch GLM-4.7 vs Qwen3.5-122B-A10B
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.
Last updated September 27, 2026