GLM 4.7 vs Hy4
Hy4 leads GLM 4.7 on coding, 65.2 to 55.1 on the Vibe Coding Index, and Hy4 costs 1.8x less per output token ($1.2505 vs $2.20 per million). Updated November 5, 2026; no benchmark has tested both models yet.
- Coding
- 55.1
- Overall
- 62.3
- Output $/M
- $2.20
- Coding
- 65.2
- Overall
- No data
- Output $/M
- $1.2505
GLM 4.7 or Hy4: which to pick
GLM 4.7 scores 55.1 and Hy4 65.2 on the Vibe Coding Index, but no coding benchmark measured both, so the gap is directional, not a ranking.
Pick Hy4 for output tokens 1.8x cheaper ($1.2505 vs $2.20 per million) and a larger context window (1.05M against 205K tokens).
No benchmark has tested both yet. GLM 4.7 has results on LMArena WebDev, AA Coding Index and LiveCodeBench (Vals AI); Hy4 on Terminal-Bench 4 (Vals AI), Vibe Code Bench (Vals AI) and Tax Agent Bench (Vals AI). Compare them on price and context instead.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
55.1 against 65.2, from different benchmarks with none in common.
Directional only
Reasoning
GPQA Diamond
No call
Only GLM 4.7 has a GPQA Diamond result, 80.0%.
Directional only
Math
AIME
No call
Only GLM 4.7 has a AIME result, 93.3%.
Directional only
Knowledge
MMLU Pro
No call
Only GLM 4.7 has a MMLU Pro result, 82.7%.
Directional only
Web design
Design Arena: websites
No call
Only GLM 4.7 has a Design Arena: websites result, 1224.
Directional only
General
Vals Index
No call
Only Hy4 has a Vals Index result, 59.4%.
Directional only
Long documents
Listed context window
Hy4
Hy4 takes 1.05M tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Hy4
GLM 4.7 $0.0017, Hy4 $0.0010 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GLM 4.7 has the number, $0.29.
Directional only
At a glance
- Coding index
- GLM 4.7 55.1 from 2 benchmarks, Hy4 65.2 from 2 benchmarks.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- GLM 4.7 $2.20 against Hy4 $1.2505 per million output tokens, 1.8x apart.
- Context window
- GLM 4.7 takes 205K tokens, Hy4 1.05M.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
CodingDirectional onlySix of these boards feed the Vibe Coding Index15 boards measured
| Benchmark | GLM 4.7 | Hy4 | Leader |
|---|---|---|---|
| LMArena WebDev | 1435 | Not measured | Only GLM 4.7 measured |
| AA Coding Index | 45.3 | Not measured | Only GLM 4.7 measured |
| LiveCodeBench (Vals AI) | 82.2% | Not measured | Only GLM 4.7 measured |
| SWE-bench Verified (Vals AI) | 69.4% | Not measured | Only GLM 4.7 measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 39.4% | Only Hy4 measured |
| Vibe Code Bench (Vals AI) | Not measured | 81.0% | Only Hy4 measured |
| LiveCodeBench (Artificial Analysis run) | 89.4% | Not measured | Only GLM 4.7 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 31.8% | Not measured | Only GLM 4.7 measured |
| Terminal-Bench | 33.4% | Not measured | Only GLM 4.7 measured |
| ALE-Bench | 399.5 | Not measured | Only GLM 4.7 measured |
| LMArena Text: coding | 1454 | Not measured | Only GLM 4.7 measured |
| LMArena Text: software and IT | 1453 | Not measured | Only GLM 4.7 measured |
| LMArena WebDev: React | 1420 | Not measured | Only GLM 4.7 measured |
| LMArena WebDev: HTML | 1446 | Not measured | Only GLM 4.7 measured |
| Terminal-Bench 2.0 | 33.4% | Not measured | Only GLM 4.7 measured |
| Neither model has a result on the other 35 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | GLM 4.7 | Hy4 | Leader |
|---|---|---|---|
| Epoch Capabilities Index | 143.2 | Not measured | Only GLM 4.7 measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index11 boards measured
| Benchmark | GLM 4.7 | Hy4 | Leader |
|---|---|---|---|
| Design Arena: agents building full-stack apps | 1045 | Not measured | Only GLM 4.7 measured |
| Design Arena: agents building mobile apps | 1104 | Not measured | Only GLM 4.7 measured |
| Design Arena: agents building Android apps | 1109 | Not measured | Only GLM 4.7 measured |
| Design Arena: agents building Godot games | 1058 | Not measured | Only GLM 4.7 measured |
| Tax Agent Bench (Vals AI) | Not measured | 34.4% | Only Hy4 measured |
| Legal Research Bench (Vals AI) | Not measured | 41.4% | Only Hy4 measured |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 12.5% | Only Hy4 measured |
| τ²-Bench Telecom | 95.9% | Not measured | Only GLM 4.7 measured |
| Vending-Bench 2 | $2,377 | Not measured | Only GLM 4.7 measured |
| BrowseComp-Plus | 64.7% | Not measured | Only GLM 4.7 measured |
| MCP Atlas | 58.1% | Not measured | Only GLM 4.7 measured |
| Neither model has a result on the other 33 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index9 boards measured
| Benchmark | GLM 4.7 | Hy4 | Leader |
|---|---|---|---|
| GPQA Diamond | 80.0% | Not measured | Only GLM 4.7 measured |
| GPQA Diamond (Artificial Analysis run) | 85.9% | Not measured | Only GLM 4.7 measured |
| Humanity's Last Exam (Artificial Analysis run) | 27.4% | Not measured | Only GLM 4.7 measured |
| GPQA Diamond (Epoch AI run) | 83.3% | Not measured | Only GLM 4.7 measured |
| SimpleBench | 47.7% | Not measured | Only GLM 4.7 measured |
| Chess puzzles | 21.0% | Not measured | Only GLM 4.7 measured |
| LMArena Text: hard prompts | 1443 | Not measured | Only GLM 4.7 measured |
| LMArena Text: expert | 1424 | Not measured | Only GLM 4.7 measured |
| LMArena Text: hard prompts in English | 1452 | Not measured | Only GLM 4.7 measured |
| Neither model has a result on the other 15 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards measured
| Benchmark | GLM 4.7 | Hy4 | Leader |
|---|---|---|---|
| AIME | 93.3% | Not measured | Only GLM 4.7 measured |
| MGSM (Vals AI) | 88.2% | Not measured | Only GLM 4.7 measured |
| AIME 2025 (Artificial Analysis run) | 95.0% | Not measured | Only GLM 4.7 measured |
| OTIS Mock AIME | 83.3% | Not measured | Only GLM 4.7 measured |
| ProofBench | 6.0% | Not measured | Only GLM 4.7 measured |
| LMArena Text: math | 1424 | Not measured | Only GLM 4.7 measured |
| LMArena Text: mathematical work | 1411 | Not measured | Only GLM 4.7 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index13 boards measured
| Benchmark | GLM 4.7 | Hy4 | Leader |
|---|---|---|---|
| MMLU Pro | 82.7% | Not measured | Only GLM 4.7 measured |
| LegalBench (Vals AI) | 83.4% | Not measured | Only GLM 4.7 measured |
| CaseLaw (Vals AI) | 54.9% | Not measured | Only GLM 4.7 measured |
| CorpFin (Vals AI) | 46.4% | Not measured | Only GLM 4.7 measured |
| TaxEval (Vals AI) | 68.8% | Not measured | Only GLM 4.7 measured |
| MedQA (Vals AI) | 93.7% | Not measured | Only GLM 4.7 measured |
| MedCode (Vals AI) | 32.8% | Not measured | Only GLM 4.7 measured |
| MMLU Pro (Artificial Analysis run) | 85.6% | Not measured | Only GLM 4.7 measured |
| SimpleQA Verified | 32.2% | Not measured | Only GLM 4.7 measured |
| LMArena Text: science | 1458 | Not measured | Only GLM 4.7 measured |
| LMArena Text: medicine and healthcare | 1469 | Not measured | Only GLM 4.7 measured |
| LMArena Text: legal and government | 1444 | Not measured | Only GLM 4.7 measured |
| LMArena Text: business and finance | 1429 | Not measured | Only GLM 4.7 measured |
| Neither model has a result on the other 7 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards measured
| Benchmark | GLM 4.7 | Hy4 | Leader |
|---|---|---|---|
| Design Arena: websites | 1224 | Not measured | Only GLM 4.7 measured |
| Design Arena: UI components | 1194 | Not measured | Only GLM 4.7 measured |
| Design Arena: game dev | 1188 | Not measured | Only GLM 4.7 measured |
| Design Arena: data viz | 1196 | Not measured | Only GLM 4.7 measured |
| Design Arena: 3D | 1187 | Not measured | Only GLM 4.7 measured |
| Design Arena: all code categories | 1215 | Not measured | Only GLM 4.7 measured |
| Design Arena: SVG | 1139 | Not measured | Only GLM 4.7 measured |
| Design Arena: ASCII art | 1161 | Not measured | Only GLM 4.7 measured |
| Neither model has a result on the other 1 board here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index23 boards measured
| Benchmark | GLM 4.7 | Hy4 | Leader |
|---|---|---|---|
| Vals Index | Not measured | 59.4% | Only Hy4 measured |
| MedScribe (Vals AI) | 68.6% | Not measured | Only GLM 4.7 measured |
| IFBench | 67.9% | Not measured | Only GLM 4.7 measured |
| Long context reasoning (AA-LCR) | 71.0% | Not measured | Only GLM 4.7 measured |
| CL-bench | 15.9% | Not measured | Only GLM 4.7 measured |
| CL-bench Life | 10.9% | Not measured | Only GLM 4.7 measured |
| LMArena Text | 1435 | Not measured | Only GLM 4.7 measured |
| LMArena Text: instruction following | 1412 | Not measured | Only GLM 4.7 measured |
| LMArena Text: creative writing | 1401 | Not measured | Only GLM 4.7 measured |
| LMArena Text: English | 1453 | Not measured | Only GLM 4.7 measured |
| LMArena Text: non-English | 1417 | Not measured | Only GLM 4.7 measured |
| LMArena Text: Chinese | 1495 | Not measured | Only GLM 4.7 measured |
| LMArena Text: German | 1426 | Not measured | Only GLM 4.7 measured |
| LMArena Text: Japanese | 1439 | Not measured | Only GLM 4.7 measured |
| LMArena Text: Korean | 1399 | Not measured | Only GLM 4.7 measured |
| LMArena Text: French | 1432 | Not measured | Only GLM 4.7 measured |
| LMArena Text: Spanish | 1434 | Not measured | Only GLM 4.7 measured |
| LMArena Text: Russian | 1423 | Not measured | Only GLM 4.7 measured |
| LMArena Text: Polish | 1435 | Not measured | Only GLM 4.7 measured |
| LMArena Text: multi-turn | 1446 | Not measured | Only GLM 4.7 measured |
| LMArena Text: longer queries | 1432 | Not measured | Only GLM 4.7 measured |
| LMArena Text: writing and language | 1411 | Not measured | Only GLM 4.7 measured |
| LMArena Text: entertainment and media | 1401 | Not measured | Only GLM 4.7 measured |
| Neither model has a result on the other 25 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Hy4 costs less
Repository review
50K input + 3K output tokens
Hy4 costs less
Agent loop
200K input + 10K output tokens
Hy4 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Z.ai GLM 4.7 | Tencent Hy4 |
|---|---|---|
| Maker | Z.ai | Tencent |
| Weights | Open weights | Open weights |
| Released | December 22, 2025 | November 4, 2026 |
| Context window | 205K | 1.05M |
| Input $/Mtok | $0.60 | $0.417 |
| Output $/Mtok | $2.20 | $1.2505 |
| Coding index | 55.1 | 65.2 |
| Independent measurements behind it | 2 | 2 |
| Cost per solved task | $0.29 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GLM 4.7 better than Hy4 for coding?
GLM 4.7 scores 55.1 and Hy4 65.2 on the Vibe Coding Index, but no coding benchmark measured both, so the gap is directional, not a ranking. Pick Hy4 for output tokens 1.8x cheaper ($1.2505 vs $2.20 per million) and a larger context window (1.05M against 205K tokens).
Which is cheaper, GLM 4.7 or Hy4?
GLM 4.7 costs $0.60 per million input tokens and $2.20 per million output tokens; Hy4 costs $0.417 and $1.2505. Cost per solved task is known for GLM 4.7 only.
Which has the bigger context window, GLM 4.7 or Hy4?
Hy4, with 1.05M tokens against 205K.
Has any benchmark tested both GLM 4.7 and Hy4?
No benchmark has tested both yet. GLM 4.7 has results on LMArena WebDev, AA Coding Index and LiveCodeBench (Vals AI); Hy4 on Terminal-Bench 4 (Vals AI), Vibe Code Bench (Vals AI) and Tax Agent Bench (Vals AI). Compare them on price and context instead. Data as of November 5, 2026.