BlogLLM Benchmark Scores as Published, Side by Side
GLM-5.1: Benchmark Scores as Published
Every result the catalog holds for GLM-5.1: 54 tests in 12 areas, from 9 pages. 23 printed by Z.ai itself, the rest by the company named beside each number. Each number is as printed; nothing is ranked or rescored.
Developer Z.aiReleased 2026-04-07Context window 200KMax output 128KInput TextOutput TextWeights Open (MIT)Data version 2026103001, as of 2026-10-30
Knowledge Work
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GDPval-AA (Elo) | 1535 | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: thinking |
| Vals Finance Agent v1.1 | 60.7% | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | Tools: web search |
| 60.2% | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | Tools: none | |
| Vending-Bench 2 (final balance in USD) | $5634.41 | Z.ai, GLM-5.1 model cardchecked 2026-10-15 | - |
| GDPval rubrics (pointwise rubric score) | 68.26% | MiniMax, MiniMax M3checked 2026-10-15 | Effort: thinking |
| SpreadsheetBench v1 | 85.2% | MiniMax, MiniMax M3checked 2026-10-15 | Effort: thinking; Harness: Claude Code |
| GDPval (metric not stated) | 54.7% | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | - |
| ProfBench (Search) | 46% | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | Tools: web search |
Agentic Coding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| SWE-bench Verified | 80.2% | Mistral AI, Mistral Medium 3.5 model cardchecked 2026-10-15; printed on 1 more page | Effort: max |
| SWE-Bench Pro | 58.4% | Z.ai, GLM-5.1 model cardchecked 2026-10-15; printed on 4 more pages | - |
| Terminal-Bench 2.1 | 69% | Z.ai, GLM-5.2 model cardchecked 2026-10-15; printed on 1 more page | - |
| 63.5% | Z.ai, GLM-5.2 model cardchecked 2026-10-15 | Harness: Terminus-2; Context: 256000 | |
| DeepSWE v1.1 | 18% | Z.ai, GLM-5.2 model cardchecked 2026-10-15 | Harness: mini-swe-agent; Context: 400000 |
| SWE-bench Multilingual | 73.3% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15; printed on 1 more page | Effort: thinking |
| Terminal-Bench 2.0 | 63.5% | Z.ai, GLM-5.1 model cardchecked 2026-10-15; printed on 2 more pages | Harness: Terminus-2 |
| 69% | Z.ai, GLM-5.1 model cardchecked 2026-10-15 | Harness: Claude Code | |
| NL2Repo-Bench | 42.7 | Z.ai, GLM-5.1 model cardchecked 2026-10-15; printed on 2 more pages | - |
| SWE-Marathon | 1% | Z.ai, GLM-5.2 model cardchecked 2026-10-15 | Context: 1000000 |
| ProgramBench | 50.9% | Z.ai, GLM-5.2 model cardchecked 2026-10-15 | Harness: Claude Code 2.1.156; Context: 400000 |
| FrontierSWE (dominance score) | 30.5 | Z.ai, GLM-5.2 model cardchecked 2026-10-15 | Context: 1000000 |
ML Engineering
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| PostTrainBench v1.1 | 20.1% | Z.ai, GLM-5.2 model cardchecked 2026-10-15 | Context: 1000000 |
Science and Math
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPQA Diamond | 86.2% | Z.ai, GLM-5.1 model cardchecked 2026-10-15; printed on 3 more pages | - |
| SciCode | 47.7% | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | - |
| IMO-AnswerBench | 83.8% | Z.ai, GLM-5.1 model cardchecked 2026-10-15; printed on 3 more pages | - |
| AIME 2026 | 95.3% | Z.ai, GLM-5.1 model cardchecked 2026-10-15; printed on 2 more pages | - |
| HMMT November 2025 | 94% | Z.ai, GLM-5.1 model cardchecked 2026-10-15; printed on 1 more page | - |
| HMMT February 2026 | 82.6% | Z.ai, GLM-5.1 model cardchecked 2026-10-15; printed on 3 more pages | - |
| CritPt | 4.6% | Z.ai, GLM-5.2 model cardchecked 2026-10-15; printed on 1 more page | - |
| MathArena Apex Shortlist | 72.4% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15; printed on 1 more page | Effort: thinking |
| MathArena Apex | 11.5% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: thinking |
| GPQA | 86.1% | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | Tools: none |
Long Context
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| AA-LCR | 66.9% | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | - |
Cybersecurity
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| CyberGym | 68.7% | Z.ai, GLM-5.1 model cardchecked 2026-10-15 | - |
General Knowledge and Reasoning
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Humanity's Last Exam (no tools) | 31% | Z.ai, GLM-5.1 model cardchecked 2026-10-15; printed on 3 more pages | Tools: none |
| MMLU-Pro | 86% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15; printed on 1 more page | Effort: thinking |
| Humanity's Last Exam (with tools) | 52.3% | Z.ai, GLM-5.1 model cardchecked 2026-10-15; printed on 3 more pages | Tools: tools |
| AA-Omniscience Accuracy | 31.3% | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | - |
| SimpleQA Verified | 38.1% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: thinking |
| AA-Omniscience Non-Hallucination | 66.8% | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | - |
| Chinese SimpleQA | 75% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: thinking |
Code Generation
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| LiveCodeBench v6 | 85.7% | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | - |
| IOI 2025 (total points) | 456.5 | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | - |
Tool Use and Workflows
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Toolathlon | 40.7% | Z.ai, GLM-5.1 model cardchecked 2026-10-15; printed on 2 more pages | - |
| τ³-bench Banking | 16.2% | Mistral AI, Mistral Medium 3.5 model cardchecked 2026-10-15; printed on 1 more page | Effort: max; Harness: gpt-5.2 user simulator (low), 4 trials; terminal- or embedding-based agentic search retrieval, highest score |
| MCP Atlas (public set) | 71.8% | Z.ai, GLM-5.1 model cardchecked 2026-10-15; printed on 3 more pages | - |
| Claw-Eval pass^3 | 62.7% | MiniMax, MiniMax M3checked 2026-10-15 | Effort: thinking |
| PinchBench | 81.2% | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | - |
| τ³-bench (domain not stated) | 70.6% | Z.ai, GLM-5.1 model cardchecked 2026-10-15 | - |
| τ³-bench Airline | 79.5% | Mistral AI, Mistral Medium 3.5 model cardchecked 2026-10-15; printed on 1 more page | Effort: max; Harness: gpt-5.2 user simulator (low), 4 trials; Sierra-reported for Claude Sonnet 4.5 and Qwen3.5 |
| τ³-bench Retail | 76.3% | Mistral AI, Mistral Medium 3.5 model cardchecked 2026-10-15; printed on 1 more page | Effort: max; Harness: gpt-5.2 user simulator (low), 4 trials; Sierra-reported for Claude Sonnet 4.5 and Qwen3.5 |
| τ³-bench Telecom | 98.7% | Mistral AI, Mistral Medium 3.5 model cardchecked 2026-10-15; printed on 1 more page | Effort: max; Harness: gpt-5.2 user simulator (low), 4 trials; Sierra-reported for Claude Sonnet 4.5 and Qwen3.5 |
| τ³-bench (average) | 69.7% | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | - |
Web Search and Research
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| BrowseComp | 79.3% | Z.ai, GLM-5.1 model cardchecked 2026-10-15; printed on 4 more pages | Tools: browsing with context management |
| 68% | Z.ai, GLM-5.1 model cardchecked 2026-10-15 | Tools: browsing |
Instruction Following
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| IFBench | 76.6 | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | - |
| MultiChallenge | 63% | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | - |
Multilingual
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| MMLU-ProX | 85.8% | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | - |
| WMT24++ (XCOMET-XXL) | 84.4 | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | - |
Price
API list prices in US dollars per one million tokens, as printed on the developer's pricing page on the day checked. Cost per task is measured by Vals AI.
| Price | Value | Printed by | Setup as printed |
|---|---|---|---|
| Input | $1.4 | Z.ai, Z.AI API pricingchecked 2026-10-15 | - |
| Cached input | $0.26 | Z.ai, Z.AI API pricingchecked 2026-10-15 | - |
| Output | $4.4 | Z.ai, Z.AI API pricingchecked 2026-10-15 | - |
| Cost per taskVals AI, USD, lower is better | $2.89 | Vals AI, Vibe Code Bench v1.1 leaderboardchecked 2026-10-27 | Harness: OpenHands |
More from Z.ai
Every number here is read from the same catalog file as the benchmark table, data version 2026103001. Where one page printed the model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.