Across 6 comparable benchmarks, GLM-4.7 has better reported results on 5 and worse on 1.
Moderate evidence6 of 6 shared results countedHow we compare
Price basis: International rates vs listed rates. The price section below shows the applicable periods.
| Fact | GLM-4.7 | ERNIE 5.0 |
|---|---|---|
| Context window | 200K tokens | 128K tokens |
| Input / 1M | $0.600 | $0.840 |
| Output / 1M | $2.20 | $3.38 |
| Blended (4:1) | $0.567 | $1.35 |
| Status | Available | Available |
| Released | December 22, 2025 | November 13, 2025 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 3 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
GLM-4.7 ahead on 1 of 1 counted
No fixed-scale average — see the rows in Benchmark results
GLM-4.7 ahead on 1 of 1 counted
ERNIE 5.0 ahead on 1 of 1 counted
GLM-4.7 ahead on 1 of 1 counted
No shared comparable results for Abstract reasoning, Computer & tool use, Research & search, Long context, Multimodal, Cybersecurity.
Published scores, with matching modes where available. Gaps show GLM-4.7 relative to ERNIE 5.0. Reading the results
| Benchmark | GLM-4.7 | ERNIE 5.0 | Gap |
|---|---|---|---|
| LiveCodeBenchAlgorithmic Coding · Pass @K | 84.9Thinking · no tools | 76.2Thinking · no tools | 1.11×#26 vs #41 of 113 |
| AIME2025Mathematics · Accuracy | 95.7Thinking · no tools | 89.1Thinking · no tools | +6.6 pts#21 vs #36 of 86 |
| GPQA DiamondScientific Reasoning · Accuracy | 85.7Thinking · no tools | 86.4Thinking · no tools | −0.7 pts#77 vs #73 of 200 |
| τ²-BenchService Workflows · Accuracy | 87.4Thinking · tools | 78.8≠Thinking · no tools | +8.6 pts#6 vs #18 of 40 |
| HLEKnowledge Exams · Accuracy | 42.8Thinking · tools | 25.8≠Thinking · no tools | +17.0 pts#73 vs #92 of 151 |
| MMLU-ProKnowledge Exams · Accuracy | 84.3Thinking · no tools | 83.8Thinking · no tools | +0.5 pts#41 vs #45 of 153 |
Algorithmic Coding · Pass @K
Mathematics · Accuracy
Scientific Reasoning · Accuracy
Service Workflows · Accuracy
A dash means no result is available.
| Benchmark | GLM-4.7 | ERNIE 5.0 |
|---|---|---|
| AIME 2026 | 92.9 | — |
| CritPt | 1.7 | — |
| FrontierMath - Tier 4 | 2.1 | — |
| SWE-Bench Pro - Public | 40.6 | — |
| SWE-bench Verified | 73.8 | — |
| Terminal Bench 2.0 | 41.0 | — |
| Terminal Bench Hard | 33.3 | — |
| MCP-Atlas | 58.1 | — |
| ECI | 144 | — |
| LiveBench | 58.1 | — |
| Creative Writing | 1414 | — |
| τ³-Banking | 12.2 | — |
| SimpleBench | 47.7 | — |
| Vending-Bench 2 | 2377 | — |
| BrowseComp | 52.0 | — |
| SimpleQA | — | 74.0 |
| 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 costs58%lessthan ERNIE 5.0 per million tokens — 2.4× cheaper.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
ERNIE 5.0: International pricing. context_length <= 32000 Official Baidu AI Cloud International Qianfan pay-as-you-go price for ERNIE 5.0 text input, input up to 32K tokens. Verified 2026-09-15; the page does not publish the date this price took effect. Official Baidu AI Cloud International Qianfan pay-as-you-go price for ERNIE 5.0 text output, input up to 32K tokens. Verified 2026-09-15; the page does not publish the date this price took effect. context_length > 32000; context_length <= 128000 Official Baidu AI Cloud International Qianfan pay-as-you-go price for ERNIE 5.0 text input, input above 32K and up to 128K tokens. Verified 2026-09-15; the page does not publish the date this price took effect. Official Baidu AI Cloud International Qianfan pay-as-you-go price for ERNIE 5.0 text output, input above 32K and up to 128K tokens. Verified 2026-09-15; the page does not publish the date this price took effect.
| Price / 1M tokens | GLM-4.7 | ERNIE 5.0 | Ratio |
|---|---|---|---|
| Input | $0.60 | $0.84 | 0.71× |
| Output | $2.20 | $3.38 | 0.65× |
| Cached input | $0.11 | — | — |
| Cache write | — | — | — |
| Blended | $0.567 | $1.35 | 0.42× |
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 | ERNIE 5.0 |
|---|---|---|
| Availability | Available | Available |
| Provider | Zhipu AI | Baidu |
| Model type | Chat model | Multimodal model |
| First release | December 22, 2025 | November 13, 2025 |
| Context window | 200K tokens | 128K tokens |
| Max output | 128K tokens | 64K tokens |
| Total parameters | 358B | 2.4T |
| Active parameters | 32B | — |
| Architecture | Mixture of Experts (MoE) | Mixture of Experts (MoE) |
| Documented capabilities | Reasoning, Multilingual | Reasoning, Multilingual |
| Input modalities | Text | Text, Image, Audio, Video |
| Output modalities | Text | Text, Image, Audio, Video |
| Weights | Open weights | Closed / API only |
| Licence | MIT License | — |
| Commercial use | Commercial use allowed | Proprietary |
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 ERNIE 5.0? 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.