Across 9 comparable benchmarks, GLM-4.7 has better reported results on 9 and worse on 0.
Strong evidence9 of 9 shared results countedHow we compare
Price basis: International rates vs listed rates. The price section below shows the applicable periods.
| Fact | GLM-4.7 | GLM-4.7-Flash |
|---|---|---|
| Context window | 200K tokens | 200K tokens |
| Input / 1M | $0.600 | $0.070 |
| Output / 1M | $2.20 | $0.400 |
| Blended (4:1) | $0.567 | $0.136 |
| Status | Available | Available |
| Released | December 22, 2025 | January 19, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 6 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
GLM-4.7 ahead on 2 of 2 counted
GLM-4.7 ahead on 1 of 1 counted
GLM-4.7 ahead on 2 of 2 counted
GLM-4.7 ahead on 1 of 1 counted
GLM-4.7 ahead on 2 of 2 counted
No shared comparable results for Abstract reasoning, Computer & tool use, Long context, Multimodal, Cybersecurity.
Published scores, with matching modes where available. Gaps show GLM-4.7 relative to GLM-4.7-Flash. Reading the results
| Benchmark | GLM-4.7 | GLM-4.7-Flash | Gap |
|---|---|---|---|
| SWE-bench VerifiedRepository Engineering · Accuracy | 73.8Thinking · tools | 59.2≠Thinking · no tools | +14.6 pts#42 vs #79 of 108 |
| Terminal Bench HardAgentic Development · Accuracy | 33.3Thinking · tools | 22.0Thinking · tools | +11.3 pts#58 vs #90 of 157 |
| AIME2025Mathematics · Accuracy | 95.7Thinking · no tools | 91.6Thinking · no tools | +4.1 pts#21 vs #33 of 86 |
| CritPtScientific Reasoning · Score | 1.7Thinking · no tools | 0.3Thinking · no tools | 5.67×#92 vs #124 of 134 |
| GPQA DiamondScientific Reasoning · Accuracy | 85.7Thinking · no tools | 75.2Thinking · no tools | +10.5 pts#77 vs #121 of 200 |
| BrowseCompFact Finding · Accuracy | 52.0Thinking · tools | 42.8Thinking · tools | +9.2 pts#46 vs #53 of 61 |
| Creative WritingWriting | 1414Normal · no tools | 1139Normal · no tools | 1.24×#72 vs #96 of 121 |
| τ²-BenchService Workflows · Accuracy | 87.4Thinking · tools | 79.5Thinking · tools | +7.9 pts#6 vs #16 of 40 |
| HLEKnowledge Exams · Accuracy | 42.8Thinking · tools | 14.4≠Thinking · no tools | +28.4 pts#73 vs #117 of 151 |
Repository Engineering · Accuracy
Agentic Development · Accuracy
Mathematics · Accuracy
Scientific Reasoning · Score
Scientific Reasoning · Accuracy
Fact Finding · Accuracy
Writing
Service Workflows · Accuracy
Knowledge Exams · Accuracy
A dash means no result is available.
| Benchmark | GLM-4.7 | GLM-4.7-Flash |
|---|---|---|
| AIME 2026 | 92.9 | — |
| FrontierMath - Tier 4 | 2.1 | — |
| MMLU-Pro | 84.3 | — |
| LiveCodeBench | 84.9 | — |
| SWE-Bench Pro - Public | 40.6 | — |
| Terminal Bench 2.0 | 41.0 | — |
| MCP-Atlas | 58.1 | — |
| ECI | 144 | — |
| LiveBench | 58.1 | — |
| τ²-Bench - Telecom | — | 98.8 |
| τ³-Banking | 12.2 | — |
| SimpleBench | 47.7 | — |
| Vending-Bench 2 | 2377 | — |
| MedCode | 32.8 | — |
| MedScribe | 68.6 | — |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
GLM-4.7 costs317%morethan GLM-4.7-Flash per million tokens — 4.2× the price.Using international rates vs listed rates at this token mix.
GLM-4.7: International pricing. Z.ai official (OpenRouter Z.AI first-party row), verified 2026-09-25
GLM-4.7-Flash: Listed text rates; pricing tier not confirmed.
| Price / 1M tokens | GLM-4.7 | GLM-4.7-Flash | Ratio |
|---|---|---|---|
| Input | $0.60 | $0.07 | 8.57× |
| Output | $2.20 | $0.40 | 5.50× |
| Cached input | $0.11 | — | — |
| Cache write | — | — | — |
| Blended | $0.567 | $0.136 | 4.17× |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
| Attribute | GLM-4.7 | GLM-4.7-Flash |
|---|---|---|
| Availability | Available | Available |
| Provider | Zhipu AI | Zhipu AI |
| Model type | Chat model | Reasoning model |
| First release | December 22, 2025 | January 19, 2026 |
| Context window | 200K tokens | 200K tokens |
| Max output | 128K tokens | 128K tokens |
| Total parameters | 358B | 31B |
| Active parameters | 32B | 3B |
| Architecture | Mixture of Experts (MoE) | Mixture of Experts (MoE) |
| Documented capabilities | Reasoning, Multilingual | Reasoning, Multilingual |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
| Weights | Open weights | Open weights |
| Licence | MIT License | MIT License |
| Commercial use | Commercial use allowed | Commercial use allowed |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used GLM-4.7 or GLM-4.7-Flash? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.