Data as of November 7, 2026 · How the score is built
Released Apr 7, 2026203K context
GLM-5.1
Decision readingGLM-5.1 scores 56.2 out of 100 and ranks #64 of 212. This profile shows 27 source-displayable benchmark rows; its strongest eligible category is Instruction Following at #7. API pricing is $1.4 input and $4.4 output per million tokens.
Released Apr 7, 2026 — see all recent releases
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
56.2/100
field median 50.1#64 of 212 ranked models
Public
#64of 212
Verified #38 of 77
Price
$1.40input / $4.40 output
input median $0.60blended $2.90
Speed
73tok/s
field median 92 tok/sFirst token 53.77 s
Context
203Ktokens
field median 256,000Reported for this model; direct source link not stored
Strongest published evidence
Instruction Following ranks #7. A well-rounded choice across a range of tasks.
Validate before choosing
27 published rows leave some tracked benchmark slots empty. Knowledge is its lowest eligible category at #72.
Source-linked · 27 displayable benchmark rows
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #58 of 131Percentile 56thWeight 22%10 benchmarksVerified | 45.1 | 10 benchmarks | Verified | |||
| CodingRank #53 of 157Percentile 67thWeight 20%8 benchmarksVerified | 47.5 | 8 benchmarks | Verified | |||
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| KnowledgeRank #72 of 178Percentile 60thWeight 12%4 benchmarksVerified | 52.1 | 4 benchmarks | Verified | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingRank #7 of 157Percentile 96thWeight 5%Not listedUnlisted sources | 93.8 | Not listed | Unlisted sources | |||
| MathRank #8 of 12Percentile 36thWeight 5%5 benchmarksVerified | 55.9 | 5 benchmarks | Verified |
27 of 817 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic10/10 verified
- Coding8/8 verified
- ReasoningNot measured
- MultimodalNot measured
- Knowledge4/4 verified
- MultilingualNot measured
- Inst. FollowingNot measured
- Math5/5 verified
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
GLM-5.1 category percentile values
- Agentic56th percentile
- Coding67th percentile
- ReasoningNot eligible
- MultimodalNot eligible
- Knowledge60th percentile
- MultilingualNot eligible
- Instruction following96th percentile
- Math36th percentile
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#58/131
- Coding#53/157
- ReasoningNot ranked
- MultimodalNot ranked
- Knowledge#72/178
- MultilingualNot ranked
- Inst. Following#7/157
- Math#8/12
Benchmark ledger
Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Coding8 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| SWE-bench Pro | Score58.4% | Versus best verified row Best verified: Claude Opus 5.5 · 89.9% | Gap31.5 behind | Weight26% ref. weight | Provider exact |
| LiveCodeBench (Vals)LiveCodeBench, Vals AI run | Score81.4% | Versus best verified row Best verified: Claude Fable 5.1 · 90.5% | Gap9.1 behind | Weight8% ref. weight | |
| SWE-Rebench | Score62.7% | Versus best verified row Best verified: Claude Opus 4.6 · 65.3% | Gap2.6 behind | Weight5% ref. weight | Benchmark exact |
| Terminal-Bench 2.0 | Score63.5% | Versus best verified row Best verified: GPT-5.5 · 82.0% | Gap18.5 behind | WeightScored in Agentic | Provider exact |
| NL2Repo | Score42.7% | Versus best verified row Best verified: DeepSeek V4.1 Flash 1017 · 68.2% | Gap25.5 behind | WeightDisplay only | Provider exact |
| Vibe Code BenchVibe Code Bench v1.1 | Score31.46% | Versus best verified row Best verified: Gemini 4 Argon · 91.90% | Gap60.4 behind | WeightDisplay only | Benchmark exact |
| OpenHarmony BenchOpenHarmony Bench v1.0 | Score52.3% | Versus best verified row Best verified: Qwen3.8 Max · 60.8% | Gap8.5 behind | WeightDisplay only | Benchmark exact |
| SWE-bench (Vals)SWE-bench, Vals AI run | Score76.4% | Versus best verified row Best verified: Claude Opus 5 · 97.0% | Gap20.6 behind | WeightDisplay only | Verified |
Agentic10 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| BrowseComp | Score68% | Versus best verified row Best verified: Atria Dawn Preview · 92.5% | Gap24.5 behind | Weight8% ref. weight | Provider exact |
| Terminal-Bench 2.0 | Score63.5% | Versus best verified row Best verified: GPT-5.5 · 82% | Gap18.5 behind | Weight7% ref. weight | Provider exact |
| MCP Atlas | Score71.8% | Versus best verified row Best verified: Muse Spark Open · 89.2% | Gap17.4 behind | Weight4% ref. weight | Provider exact |
| Terminal-Bench 2.1 (Vals)Terminal-Bench 2.1, Vals AI run | Score56.9% | Versus best verified row Best verified: GPT-6 Astra · 87.3% | Gap30.4 behind | Weight4% ref. weight | |
| HLE w/ toolsHumanity's Last Exam with tools | Score52.3% | Versus best verified row Best verified: Kimi K3.1 Pro · 70.0% | Gap17.7 behind | Weight3% ref. weight | Provider exact |
| τ³-bench resultsτ³-Bench Tool-Agent-User Evaluation | Score70.6% | Versus best verified row Best verified: Mercury 2.5 · 96.0% | Gap25.4 behind | Weight2% ref. weight | Provider exact |
| CyberGym | Score68.7% | Versus best verified row Best verified: MiMo-V2.6-Flash · 95.1% | Gap26.4 behind | WeightDisplay only | Benchmark exact |
| Claw-Eval | Score62.3% | Versus best verified row Best verified: Ornith-1.5-397B · 81.4% | Gap19.1 behind | WeightDisplay only | Benchmark exact |
| Gert LabsGert Labs Composite Game Benchmark | Score60.11% | Versus best verified row Best verified: Claude Opus 4.8 · 72.97% | Gap12.9 behind | WeightDisplay only | Benchmark exact |
| ResearchClawBench | Score18.2% | Versus best verified row Best verified: Claude Opus 4.8 · 21.1% | Gap2.9 behind | WeightDisplay only | Benchmark exact |
Knowledge4 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| HLEHumanity's Last Exam | Score31% | Versus best verified row Best verified: Kimi K3.1 Pro · 70% | Gap39 behind | Weight44% ref. weight | Provider exact |
| MMLU-Pro (Vals)MMLU-Pro, Vals AI run | Score86.9% | Versus best verified row Best verified: Claude Fable 5.1 · 92.4% | Gap5.5 behind | Weight6% ref. weight | Verified |
| GPQA Diamond (Vals)GPQA Diamond, Vals AI run | Score84.5% | Versus best verified row Best verified: Gemini 3.1 Pro · 95.5% | Gap11 behind | Weight2% ref. weight | |
| GPQA-DGPQA Diamond | Score86.2% | Versus best verified row Best verified: GPT-6 Astra · 96.0% | Gap9.8 behind | WeightDisplay only | Provider exact |
Math5 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| FrontierMath v2 (Tiers 1-3)FrontierMath v2 Tiers 1-3 | Score36.842% | Versus best verified row Best verified: GPT-6 Astra · 93.684% | Gap56.8 behind | WeightWeighted 30% | Benchmark exact |
| AIME26AIME 2026 | Score95.3% | Versus best verified row Best verified: GLM-5.2 · 99.2% | Gap3.9 behind | WeightWeighted 25% | Provider exact |
| HMMT Feb 2026Harvard-MIT Mathematics Tournament February 2026 | Score82.6% | Versus best verified row Best verified: Qwen3.7 Max · 97.1% | Gap14.5 behind | WeightWeighted 25% | Provider exact |
| HMMT Nov 2025Harvard-MIT Mathematics Tournament November 2025 | Score94.0% | Versus best verified row Best verified: Qwen3.6 Plus · 94.6% | Gap0.6 behind | WeightDisplay only | Provider exact |
| MMAnswerBench | Score83.8% | Versus best verified row Best verified: GLM-5.2 · 91.0% | Gap7.2 behind | WeightDisplay only | Provider exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 27 rowsWhat it costs to get this score
Published API price against the public score. The x-axis uses a log scale; the dashed path marks models that are not beaten by a cheaper, higher-scoring option. Price uses average of published input and output rates.
GLM-5.1 · 56.2 score · $2.90 blended per million tokens
The chart opens on the current model. Scroll horizontally to inspect the full price axis.
Horizontal: blended price per million tokens, log scale · Vertical: public score
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not published
- Context window
- 203K
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not sourced yet
- Availability
- Not sourced yet
- Cloud regions
- Not tracked yet
- Lifecycle
- Superseded
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing record
- Self-host
- GLM-5.1 needs ~640GB VRAM (8× NVIDIA H100 (80GB)).
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
GLM-5.1 ranks #64 of 212 on the public leaderboard with a score of 56.2/100. Its source-verified position is #38 of 77.
GLM-5.1 is a open weight model with a 203K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Official flagship agentic model released April 7, 2026. Benchmarks sourced from Z.AI official performance report.
GLM-5.1 sits in the GLM-5 family with GLM-5, GLM-5.2, GLM-5.3, GLM-5.3-Flash, GLM-5-Turbo, GLM-5V-Turbo, GLM-5 (Reasoning). Its explicit predecessor is GLM-5. 27 of 817 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Instruction Following at #7, while its lowest eligible position is Knowledge at #72. a well-rounded choice across a range of tasks.
Last updated November 7, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Where to run GLM-5.1 by API
3 hosts publish a per-token price for it. OpenRouter has the lowest output rate, $3.04 per million tokens. Prices read from each host’s own pages on October 20, 2026.
| Host | Input /1M | Output /1M | Cached /1M | Context | Listed speed |
|---|---|---|---|---|---|
| OpenRouter | $0.97 | $3.04 | $0.18 | 205K | — |
| Novita AI | $1.38 | $4.40 | $0.26 | 205K | — |
| Nebius Token Factory | $1.40 | $4.40 | — | 203K | 25 tok/s |
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Questions
How does GLM-5.1 perform overall in AI benchmarks?
GLM-5.1 ranks #64 out of 212 models on the public BenchAlign leaderboard, with a score of 56.2/100. Its evidence status is Supported, and this profile shows 27 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is GLM-5.1 good for knowledge and understanding?
GLM-5.1 ranks #72 out of 178 eligible models for knowledge and understanding, with a public category score of 52.1/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is GLM-5.1 good for coding and programming?
GLM-5.1 ranks #53 out of 157 eligible models for coding and programming, with a public category score of 47.5/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is GLM-5.1 good for mathematics?
GLM-5.1 ranks #8 out of 12 eligible models for mathematics, with a public category score of 55.9/100. That places it in the current top ten for this category. Check the underlying rows before treating the aggregate as a workload guarantee.
Is GLM-5.1 good for agentic tool use and computer tasks?
GLM-5.1 ranks #58 out of 131 eligible models for agentic tool use and computer tasks, with a public category score of 45.1/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is GLM-5.1 open source?
GLM-5.1 is an open-weight model from Z.AI. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Which sibling models are related to GLM-5.1?
GLM-5.1 belongs to the GLM-5 family. Related tracked variants include GLM-5, GLM-5.2, GLM-5.3, plus 4 more. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does GLM-5.1 have full benchmark coverage on BenchLM?
No. GLM-5.1 currently has 44 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of GLM-5.1?
GLM-5.1 has a reported context window of 203K in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.