Across 13 comparable benchmarks, GPT-5.1 has better reported results on 12 and worse on 1.
Moderate evidence13 of 13 shared results countedHow we compare
Price basis: International rates vs standard rates. The price section below shows the applicable periods.
| Fact | GLM-4.6 | GPT-5.1 |
|---|---|---|
| Context window | 200K tokens | 400K tokens |
| Input / 1M | $0.600 | $1.25 |
| Output / 1M | $2.20 | $10.00 |
| Blended (4:1) | $0.567 | $2.19 |
| Status | Available | Deprecated |
| Released | September 30, 2025 | November 12, 2025 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 7 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
GPT-5.1 ahead on 4 of 4 counted
Split 1–1 of 2 counted
GPT-5.1 ahead on 2 of 2 counted
GPT-5.1 ahead on 1 of 1 counted
GPT-5.1 ahead on 1 of 1 counted
No fixed-scale average — see the rows in Benchmark results
No shared comparable results for Abstract reasoning, Computer & tool use, Long context, Multimodal, Cybersecurity.
Published scores, with matching modes where available. Gaps show GLM-4.6 relative to GPT-5.1. Reading the results
| Benchmark | GLM-4.6 | GPT-5.1 | Gap |
|---|---|---|---|
| LiveCodeBenchAlgorithmic Coding · Pass @K | 84.5Thinking · tools | 86.8≠Thinking High · no tools | 0.97×#27 vs #19 of 113 |
| SWE-bench VerifiedRepository Engineering · Accuracy | 68.0Normal · no tools | 76.3≠Thinking High · no tools | −8.3 pts#68 vs #32 of 108 |
| Terminal Bench HardAgentic Development · Accuracy | 28.8Normal · tools | 45.5≠Thinking High · tools | −16.7 pts#72 vs #20 of 157 |
| Vibe Code Bench v1.1Code Generation & Editing · Pass rate (%) | 3.1Unspecified Reasoning · tools | 24.6≠Thinking High · tools | −21.5 pts#113 vs #82 of 121 |
| AIME2025Mathematics · Accuracy | 98.6Thinking · no tools | 94.2≠Thinking High · tools | +4.4 pts#15 vs #26 of 86 |
| FrontierMath - Tier 4Mathematics · Accuracy | 2.1Normal · no tools | 12.5≠Thinking High · no tools | −10.4 pts#31 vs #13 of 50 |
| CritPtScientific Reasoning · Score | 1.1Thinking · no tools | 4.9≠Thinking High · no tools | 0.22×#103 vs #71 of 134 |
| GPQA DiamondScientific Reasoning · Accuracy | 82.9Thinking · tools | 88.1≠Thinking · no tools | −5.2 pts#96 vs #65 of 200 |
| BrowseCompFact Finding · Accuracy | 45.1Thinking · tools | 50.8≠Thinking High · no tools | −5.7 pts#50 vs #48 of 61 |
| τ³-BankingService Workflows · Score | 13.4Thinking · tools | 15.9≠Thinking High · tools | 0.84×#80 vs #69 of 120 |
| HLEKnowledge Exams · Accuracy | 30.4Thinking · tools | 42.7≠Thinking High · tools + web | −12.3 pts#88 vs #74 of 151 |
| MMLU-ProKnowledge Exams · Accuracy | 83.2Thinking · no tools | 87.0≠Thinking High · no tools | −3.8 pts#47 vs #16 of 153 |
| LiveBenchCross-capability Suites · Accuracy | 55.2Normal · no tools | 72.0≠Thinking High · no tools | −16.9 pts#91 vs #50 of 106 |
Algorithmic Coding · Pass @K
Repository Engineering · Accuracy
Agentic Development · Accuracy
Code Generation & Editing · Pass rate (%)
Mathematics · Accuracy
Mathematics · Accuracy
Scientific Reasoning · Score
Scientific Reasoning · Accuracy
Fact Finding · Accuracy
Service Workflows · Score
A dash means no result is available.
| Benchmark | GLM-4.6 | GPT-5.1 |
|---|---|---|
| FrontierMath | — | 26.7 |
| IMO-ProofBench Advanced | — | 7.1 |
| MathArena Apex | — | 1.0 |
| GSO | — | 13.7 |
| IC SWE-Lancer (Diamond) | — | 69.7 |
| SWE-Bench Pro - Public | — | 50.8 |
| Terminal Bench 2.0 | — | 47.6 |
| Terminal-Bench 1.0 | 40.5 | — |
| WeirdML v2 | — | 60.8 |
| MCP-Atlas | — | 50.1 |
| ECI | — | 150 |
| Text Arena (Coding) | — | 1387 |
| Creative Writing | 1412 | — |
| MMMU | — | 85.4 |
| MMMU-Pro | — | 79.0 |
| VPCT | — | 58.7 |
| SAGE | — | 43.2 |
| τ²-Bench | 75.9 | — |
| τ²-Bench - Telecom | 70.5 | — |
| ARC-AGI-1 | — | 72.8 |
| ARC-AGI-2 | — | 17.6 |
| SimpleBench | — | 53.2 |
| Vending-Bench 2 | — | 1473 |
| MedCode | — | 52.7 |
| MedScribe | — | 88.1 |
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-4.6 costs74%lessthan GPT-5.1 per million tokens — 3.9× cheaper.Using international rates vs standard rates at this token mix.
GLM-4.6: International pricing. Z.ai official (OpenRouter Z.AI first-party row), verified 2026-09-25
GPT-5.1: Standard pricing. OpenAI official pricing (developers.openai.com/api/docs/pricing) verified 2026-11-13; standard tier; Deprecated; shutdown 2027-04-01 (replacement: gpt-6-sol)
| Price / 1M tokens | GLM-4.6 | GPT-5.1 | Ratio |
|---|---|---|---|
| Input | $0.60 | $1.25 | 0.48× |
| Output | $2.20 | $10.00 | 0.22× |
| Cached input | $0.11 | $0.125 | 0.88× |
| Cache write | — | — | — |
| Blended | $0.567 | $2.19 | 0.26× |
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.
GLM-4.6 relative to GPT-5.1
No matching recorded settings for a cost summary.
Summary: 0 of 1 shared benchmarks have matching recorded settings and sources. The average is a geometric mean of 0 positive-cost ratios, one equal weight per benchmark. This benchmark set can include related tests and indexes; it is not a workload cost estimate.
Settings or sources differ
Settings or sources differ
Settings or sources differ or are not recorded; interpret the comparison with care.
GLM-4.6
GPT-5.1
| Attribute | GLM-4.6 | GPT-5.1 |
|---|---|---|
| Availability | Available | Deprecated |
| Provider | Zhipu AI | OpenAI |
| Model type | Chat model | Reasoning model |
| First release | September 30, 2025 | November 12, 2025 |
| Context window | 200K tokens | 400K tokens |
| Max output | 128K tokens | 128K tokens |
| Total parameters | 355B | — |
| Active parameters | 32B | — |
| Architecture | Mixture of Experts (MoE) | Undisclosed |
| Documented capabilities | Reasoning, Multilingual | Reasoning, Multilingual |
| Input modalities | Text | Text, Image |
| Output modalities | Text | Text |
| 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-4.6 or GPT-5.1? 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.