# Qwen3.8-27B

Alibaba · Open Weight · rank 74 · bench-align-v5 · Self-hosted

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/models/qwen3-8-27b  
JSON: https://modelchoice.dev/api/model/qwen3-8-27b

## Facts

| Field | Value | Evidence |
| --- | --- | --- |
| Canonical id | `qwen3-8-27b` | — |
| Overall score | 55 | Observed 2026-11-21 · source benchlm:models |
| Verified score (BenchLM): a separate BenchLM figure, not the overall score | 73 | Observed 2026-11-21 · source benchlm:models |
| Context window | 262K tokens | Observed 2026-11-21 · source benchlm:models |
| Release date | 2026-08-05 | Observed 2026-11-21 · source benchlm:models |
| Access type | Open Weight | — |
| Blended $/1M (75% input / 25% output) | Unavailable | Derived from the input and output rates below |

## Capability evidence

Seven axes from the ranking source. An axis the source did not score is unavailable, not zero. Beside each score is BenchLM's separate verified score for that axis; the two are published side by side and are not interchangeable.

| Axis | Score | Evidence | Verified (BenchLM) | Verified evidence |
| --- | --- | --- | --- | --- |
| Agentic | 82.6 | Observed 2026-11-21 · source benchlm:models | 80.2 | Observed 2026-11-21 · source benchlm:models |
| Coding | 61.3 | Observed 2026-11-21 · source benchlm:models | 60.7 | Observed 2026-11-21 · source benchlm:models |
| Knowledge | 51.4 | Observed 2026-11-21 · source benchlm:models | 49.4 | Observed 2026-11-21 · source benchlm:models |
| Reasoning | 80.5 | Observed 2026-11-21 · source benchlm:models | 80.5 | Observed 2026-11-21 · source benchlm:models |
| Multimodal & Grounded | 81.7 | Observed 2026-11-21 · source benchlm:models | 81.7 | Observed 2026-11-21 · source benchlm:models |
| Instruction Following | 87.8 | Observed 2026-11-21 · source benchlm:models | 87.8 | Observed 2026-11-21 · source benchlm:models |
| Math | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |

## Runtime service evidence

Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim. Regional or per-endpoint measurements appear only when the API supplies them; none are modelled.

| Measurement | Value | Observed | Last good | Evidence |
| --- | --- | --- | --- | --- |
| Time to first token | 145.7 s | 2026-11-21 | 2026-11-21 | Observed 2026-11-21 · source benchlm:speed |
| Throughput | 51 tok/s | 2026-11-21 | 2026-11-21 | Observed 2026-11-21 · source benchlm:speed |

## Endpoint and price matrix

Every published price component, including cache reads and writes.

| Component | USD | Evidence |
| --- | --- | --- |
| Input / 1M tokens | Unavailable | Unavailable · source benchlm:pricing |
| Output / 1M tokens | Unavailable | Unavailable · source benchlm:pricing |
| Cache read / 1M tokens | Unavailable | Unavailable · source benchlm:pricing |
| Cache write / 1M tokens | Unavailable | Unavailable · source openrouter:pricing |
| Blended / 1M (75% input / 25% output) | Unavailable | Derived — from the input and output rates above; it has no source record of its own |
| Cost per successful task (LiveBench) | Unavailable | Unavailable · source livebench:table |

**Self-hosted listing.** Qwen publishes Qwen3.8-27B under Apache-2.0 for self-hosting and has not published a first-party hosted token rate for the exact model. BenchLM represents the open-weight row as self-host/free-per-token before infrastructure costs. Qwen Cloud says hosted access is coming soon, so the pricing row does not inherit Qwen3.8 Max rates. No hosted token rate was published for this model, so its per-token price is unavailable rather than zero.

## Workload-aware monthly cost example

10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. Derived here from the published rates above by this site's own calculator — not a figure any source published.

| Field | Value |
| --- | --- |
| Modelled monthly cost | Unavailable |
| Modelled tokens | Unavailable |
| Reason | The applicable input rate is unavailable. |

## Benchmark record

78 matched benchmark rows with their published value, unit, and provenance.

### Knowledge

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| GPQA (Graduate-Level Google-Proof Q&A) | 89.2 | 448 questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |
| GPQA-D (GPQA Diamond) | 89.2 | Graduate-level science questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |
| HLE (Humanity's Last Exam) | 30.8 | Expert-level questions | Frontier expert level | [Humanity's Last Exam](https://lastexam.ai/) |
| Artificial Analysis Intelligence Index | 20.1 | Cross-benchmark intelligence index | Display-only external reference | [Artificial Analysis](https://artificialanalysis.ai/) |
| AA-GPQA Diamond (Artificial Analysis GPQA Diamond) | 90.5 | Graduate-level science questions | Graduate-level science reasoning | [Artificial Analysis GPQA Diamond Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/gpqa-diamond) |
| AA-HLE (Artificial Analysis Humanity's Last Exam) | 33.9 | Expert-level questions | Frontier expert reasoning | [Artificial Analysis Humanity's Last Exam Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/hle) |
| AA-Omniscience Index (Artificial Analysis Omniscience Index) | -6.4 | Knowledge questions | Broad factual knowledge | [AA-Omniscience: Knowledge and Hallucination Benchmark](https://artificialanalysis.ai/evaluations/omniscience) |
| AA-Omniscience Accuracy (Artificial Analysis Omniscience Accuracy) | 17.3 | Knowledge questions | Broad knowledge | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA-Omniscience Hallucination Rate (Artificial Analysis Omniscience Hallucination Rate) | 28.6 | Knowledge questions | Factuality | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| HLE w/o tools (Humanity's Last Exam without tools) | 30.8 | Expert-level questions | Frontier expert level | [Introducing GPT-5.4 mini and nano](https://openai.com/index/introducing-gpt-5-4-mini-and-nano/) |
| GPQA Diamond (Vals) (GPQA Diamond, Vals AI run) | 88.9 | Graduate-level science questions | Expert reasoning | [Vals AI GPQA Diamond, Vals AI run leaderboard](https://www.vals.ai/benchmarks/gpqa) |
| MMLU-Pro (Vals) (MMLU-Pro, Vals AI run) | 84.3 | Academic multiple-choice questions | Broad academic knowledge | [Vals AI MMLU-Pro, Vals AI run leaderboard](https://www.vals.ai/benchmarks/mmlu_pro) |

### Coding

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Terminal-Bench 2.1 | 73.0 | Terminal-based software-agent tasks | Professional software engineering | [Terminal-Bench](https://www.tbench.ai/) |
| LiveCodeBench v6 | 90.3 | Fresh programming problems | Competitive programming level | [LiveCodeBench official repository and release documentation](https://github.com/LiveCodeBench/LiveCodeBench) |
| SWE-bench Pro | 61.7 | 1,865 repository problems | Long-horizon professional engineering | [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://arxiv.org/abs/2509.16941) |
| VulcanBench v3 | 82.6 | 23 post-cutoff repository tasks in the v3 report | Professional multi-file software engineering | [VulcanBench](https://github.com/morganlinton/VulcanBench/tree/main) |
| Bug Hunt Bench | 15.0 | 105 planted bugs across two production TypeScript repositories | Blind production-repository bug finding and repair | [Bug Hunt Bench method, caveats, and definitions](https://bughunt.productcompass.pm/method) |
| NL2Repo | 42.3 | Natural language to repository tasks | System-level software comprehension | [MiniMax M2.7: Early Echoes of Self-Evolution](https://www.minimax.io/news/minimax-m27-en) |
| AA Coding Index (Artificial Analysis Coding Index) | 68.1 | Cross-benchmark coding index | Display-only external reference | [Artificial Analysis model leaderboards](https://artificialanalysis.ai/leaderboards/models) |
| AA-SciCode (Artificial Analysis SciCode) | 46.6 | Scientific coding subproblems | Scientific programming | [Artificial Analysis SciCode Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/scicode) |
| LiveCodeBench (Vals) (LiveCodeBench, Vals AI run) | 84.0 | Competitive programming problems (easy, medium, hard) | Frontier coding | [Vals AI LiveCodeBench, Vals AI run leaderboard](https://www.vals.ai/benchmarks/lcb) |
| SWE-bench (Vals) (SWE-bench, Vals AI run) | 86.0 | Real repository issues by human time bucket | Frontier coding agents | [Vals AI SWE-bench, Vals AI run leaderboard](https://www.vals.ai/benchmarks/swebench) |
| DeepSWE | 42.2 | 113 software engineering tasks across 91 repositories and 5 languages | Long-horizon software engineering | [DeepSWE benchmark blog](https://deepswe.datacurve.ai/blog) |

### Reasoning

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AA-LCR (Artificial Analysis Long Context Reasoning) | 82.0 | Long-context reasoning tasks | Long-context reasoning | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| MLCR-AA (Medical Long Context Reasoning (MLCR-AA)) | 22.8 | Long, fragmented medical-record reasoning | Long-context medical reasoning | [Medical Long Context Reasoning (MLCR-AA)](https://artificialanalysis.ai/evaluations/mlcr-aa) |
| CritPt (Critical Physics Tasks) | 5.4 | Research-level physics questions | Research-level physics reasoning | [CritPt Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/critpt) |

### Instruction Following

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| IFBench (Instruction Following Benchmark) | 79.5 | — | — | [BenchLM](https://benchlm.ai/benchmarks/ifbench) |

### Agentic

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AA Briefcase (Artificial Analysis Briefcase) | 1391 | Professional knowledge-work tasks | Professional work | [Artificial Analysis Briefcase Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/aa-briefcase) |
| AA AutomationBench (Artificial Analysis AutomationBench) | 48.2 | Business-process automation tasks | Agentic automation | [Artificial Analysis AutomationBench Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/automationbench-aa) |
| AA EnterpriseOps-Gym (Artificial Analysis EnterpriseOps-Gym) | 44.2 | Enterprise operations workflows | Enterprise agent operations | [Artificial Analysis EnterpriseOps-Gym Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa) |
| AA Tau3 Banking (Artificial Analysis Tau3-Banking) | 48.0 | Banking tool-use workflows | Agentic banking workflows | [Artificial Analysis Tau3-Banking Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/tau3-banking) |
| Terminal-Bench 2.1 | 73.0 | Terminal-based software-agent tasks | Professional software engineering | [Terminal-Bench](https://www.tbench.ai/) |
| GDPval-AA | 1426 | Agentic real-world work tasks | Professional agentic workflows | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| GDPval-AA (GDPval-AA normalized) | 45.9 | Economically valuable tasks | Professional agentic workflows | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA Agentic Index (Artificial Analysis Agentic Index) | 46.5 | Cross-benchmark agentic index | Display-only external reference | [Artificial Analysis model leaderboards](https://artificialanalysis.ai/leaderboards/models) |
| AA Terminal-Bench 4.0 (Artificial Analysis Terminal-Bench v4.0) | 5.6 | Terminal-based agent tasks | Agentic software engineering | [Artificial Analysis Terminal-Bench v4.0 Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/terminalbench-v4-0) |
| GDP.pdf (Artificial Analysis GDP.pdf) | 16.4 | Professional document-production tasks | Professional knowledge work | [GDP.pdf Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/gdp-pdf) |
| OSWorld-Verified | 84.3 | 369 real-world computer tasks (361 when eight Google Drive tasks are excluded) | Multi-step desktop and cross-application workflows | [OSWorld](https://os-world.github.io/) |
| JobBench | 33.4 | 130 tasks across 35 occupations | Professional multi-source workflows | [JobBench: Aligning Agent Work With Human Will](https://arxiv.org/abs/2605.26329) |
| AndroidWorld | 81.9 | Android app workflows | Complex mobile task completion | [GLM-5V-Turbo](https://docs.z.ai/guides/vlm/glm-5v-turbo) |
| Agents' Last Exam | 42.9 | Agent tasks | Advanced agentic work | [DeepSeek V4 Flash 0731 update](https://api-docs.deepseek.com/zh-cn/updates/) |
| CoWorkBench | 70.7 | Long-horizon professional workflows | Cross-domain professional work | [Qwen3.8-Max: A New Bar for Coding and Cowork](https://qwen.ai/blog?id=qwen3.8) |
| WebArena-Verified (WebArena-Verified Browser Agent Benchmark) | 64.8 | 812 verified tasks; separate 258-task Hard subset | Audited stateful browser work | [WebArena-Verified: A Fully Audited Benchmark for Web Agents](https://openreview.net/forum?id=94tlGxmqkN) |
| Terminal-Bench 2.1 (Vals) (Terminal-Bench 2.1, Vals AI run) | 58.4 | Difficult terminal tasks | Frontier agentic | [Vals AI Terminal-Bench 2.1, Vals AI run leaderboard](https://www.vals.ai/benchmarks/terminal-bench-2-1) |
| MazeBench (MazeBench: visual spatial reasoning in a 3D open world) | 0 | 100 hidden gems across 256 rooms in one open world | Long-horizon spatial planning, with single puzzles that can take over one hundred moves | [MazeBench Results](https://mazebench.com/blog?post=maze-bench-results) |
| AA Cyber Index (Artificial Analysis Cyber Index) | 12.7 | Three defensive cybersecurity evaluations | Real-world vulnerability discovery and patching | [Artificial Analysis Cyber Index](https://artificialanalysis.ai/evaluations/artificial-analysis-cyber-index) |
| CWE-Bench-AA (Artificial Analysis CWE-Bench-AA) | 26.7 | Real-world vulnerability patching tasks | Automated vulnerability remediation | [CWE-Bench-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/cwe-bench-aa) |
| DeepsecBench-AA (Artificial Analysis DeepsecBench-AA) | 11.5 | Vulnerability discovery in real codebases | Security code review | [DeepsecBench-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/deepsecbench-aa) |
| CyberGym-E2E-AA (Artificial Analysis CyberGym-E2E-AA) | 0.0 | 131 end-to-end vulnerability reproduction and patching tasks | Real-world cybersecurity | [CyberGym-E2E-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/cybergym-e2e-aa) |

### Multimodal & Grounded

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AA-MMMU-Pro (Artificial Analysis MMMU-Pro) | 76.3 | Multimodal academic reasoning | Frontier multimodal | [Artificial Analysis MMMU-Pro Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/mmmu-pro) |
| MathVision w/ Python (MathVision with Python) | 94.6 | Visual mathematics problems with Python | Advanced multimodal mathematics | [Kimi K3: Open Frontier Intelligence](https://www.kimi.com/blog/kimi-k3) |
| BabyVision w/ Python (BabyVision with Python) | 85.6 | Visual perception tasks with Python | Fine-grained visual perception | [Kimi K3: Open Frontier Intelligence](https://www.kimi.com/blog/kimi-k3) |
| OmniDocBench 1.5 | 91.1 | Document understanding tasks | Grounded document reasoning | [Introducing GPT-5.4 mini and nano](https://openai.com/index/introducing-gpt-5-4-mini-and-nano/) |
| RealWorldQA | 85.9 | Real-world visual question answering | General visual reasoning | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |
| MathVision | 90.0 | Visually grounded math problems | Advanced multimodal mathematics | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |
| ERQA | 65.5 | Evidence-based visual QA | Grounded multimodal reasoning | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |
| Vision2Web | 62.9 | Screenshot-to-web tasks | Multimodal web generation | [GLM-5V-Turbo](https://docs.z.ai/guides/vlm/glm-5v-turbo) |
| CharXiv (CharXiv Reasoning) | 90.2 | Scientific chart reasoning | Scientific visualization reasoning | [CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs](https://charxiv.github.io/) |
| CharXiv w/o tools (CharXiv Reasoning without tools) | 83.7 | Scientific chart reasoning (tool-free) | Scientific visualization reasoning | [CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs](https://charxiv.github.io/) |
| BabyVision | 65.7 | Visual perception tasks | Fine-grained visual perception | [Muse Spark 1.1 Evaluation Report](https://ai.meta.com/static-resource/muse-spark-1-1-evaluation-report) |
| ParseBench-1 (ParseBench-1: document parsing for AI agents (LlamaIndex leaderboard, first release)) | 69.03 | 2,078 human-verified enterprise pages from insurance, finance and government documents | No method is strong on all five dimensions; charts and visual grounding separate the field | [ParseBench: A Document Parsing Benchmark for AI Agents](https://arxiv.org/abs/2604.08538) |
| ExtractBench (LlamaIndex) (ExtractBench: schema-guided enterprise document extraction (LlamaIndex leaderboard)) | 89.75 | 370 documents, 4,869 pages, 8 business domains, 67 document types, each with a JSON Schema | Short documents are near solved; long record lists and grounding separate systems | [ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction](https://arxiv.org/abs/2607.29677) |
| ParseBench-2 (ParseBench-2: severity-aware document parsing (LlamaIndex leaderboard)) | 74.48 | 4,317 page-level test cases from 2,645 documents in 13 datasets | Charts and visual grounding separate the field; several systems that lead on text and tables score near zero on charts | [ParseBench-2: Severity-Aware Evaluation of Document Parsing](https://www.parsebench.ai/parsebench-2.pdf) |

### external

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| WinoGrande (Perplexity panel) | 73.10 | Ambiguous-reference resolution | Depends on the sampled tasks and label mapping | [Perplexity Decider v1 27B model card](https://huggingface.co/perplexity-ai/pplx-decider-v1-27b/blob/9ce1abcf1f00209405376b5bcc81225c8f8cf514/README.md) |
| FinancialPhraseBank (Perplexity panel) | 75.68 | Financial sentiment classification | Depends on the sampled tasks and label mapping | [Perplexity Decider v1 27B model card](https://huggingface.co/perplexity-ai/pplx-decider-v1-27b/blob/9ce1abcf1f00209405376b5bcc81225c8f8cf514/README.md) |
| RAGTruth (Perplexity panel) | 61.53 | Unsupported-claim detection | Depends on the sampled tasks and label mapping | [Perplexity Decider v1 27B model card](https://huggingface.co/perplexity-ai/pplx-decider-v1-27b/blob/9ce1abcf1f00209405376b5bcc81225c8f8cf514/README.md) |
| JudgeBench (Perplexity panel) | 68.86 | Response-pair judgment | Depends on the sampled tasks and label mapping | [Perplexity Decider v1 27B model card](https://huggingface.co/perplexity-ai/pplx-decider-v1-27b/blob/9ce1abcf1f00209405376b5bcc81225c8f8cf514/README.md) |
| BBH (Perplexity panel) | 72.80 | Challenging reasoning tasks | Depends on the sampled tasks and label mapping | [Perplexity Decider v1 27B model card](https://huggingface.co/perplexity-ai/pplx-decider-v1-27b/blob/9ce1abcf1f00209405376b5bcc81225c8f8cf514/README.md) |
| JevBench public hard (Perplexity panel) | 72.28 | Public-hard decision accuracy | Depends on the sampled tasks and label mapping | [Perplexity Decider v1 27B model card](https://huggingface.co/perplexity-ai/pplx-decider-v1-27b/blob/9ce1abcf1f00209405376b5bcc81225c8f8cf514/README.md) |
| TabFact (Perplexity panel) | 78.60 | Table-based fact verification | Depends on the sampled tasks and label mapping | [Perplexity Decider v1 27B model card](https://huggingface.co/perplexity-ai/pplx-decider-v1-27b/blob/9ce1abcf1f00209405376b5bcc81225c8f8cf514/README.md) |
| ContractNLI (Perplexity panel) | 80.78 | Contract hypothesis classification | Depends on the sampled tasks and label mapping | [Perplexity Decider v1 27B model card](https://huggingface.co/perplexity-ai/pplx-decider-v1-27b/blob/9ce1abcf1f00209405376b5bcc81225c8f8cf514/README.md) |
| Circa (Perplexity panel) | 87.00 | Indirect yes/no answer interpretation | Depends on the sampled tasks and label mapping | [Perplexity Decider v1 27B model card](https://huggingface.co/perplexity-ai/pplx-decider-v1-27b/blob/9ce1abcf1f00209405376b5bcc81225c8f8cf514/README.md) |
| Belebele (Perplexity panel) | 93.20 | Passage comprehension | Depends on the sampled tasks and label mapping | [Perplexity Decider v1 27B model card](https://huggingface.co/perplexity-ai/pplx-decider-v1-27b/blob/9ce1abcf1f00209405376b5bcc81225c8f8cf514/README.md) |
| TruthfulQA binary (Perplexity panel) | 82.80 | Binary truthfulness classification | Depends on the sampled tasks and label mapping | [Perplexity Decider v1 27B model card](https://huggingface.co/perplexity-ai/pplx-decider-v1-27b/blob/9ce1abcf1f00209405376b5bcc81225c8f8cf514/README.md) |
| Perplexity Decision Panel | 74.76 | 11 decision task families | Depends on the sampled tasks and label mapping | [Perplexity Decider v1 27B model card](https://huggingface.co/perplexity-ai/pplx-decider-v1-27b/blob/9ce1abcf1f00209405376b5bcc81225c8f8cf514/README.md) |
| BabaIsBench (BabaIsBench (Baba Is You intro levels, pass@1)) | 21 | 8 intro levels of Baba Is You, three attempts per level (Stage 0); 15 further levels run once (Stage 1) | Rule-rewriting puzzles that need planning over many moves | [Baba Is Solved by Fable 5 and GPT-5.6 Sol, but at what cost? (Quesma)](https://quesma.com/blog/baba-is-bench/) |
| NYT Connections (NYT Connections LLM Benchmark (extended version)) | 54.5 | 940 NYT Connections puzzles, each with up to four added trick words | Wordplay, word knowledge and decoys that fit almost-but-not-quite | [NYT Connections LLM Benchmark (Lech Mazur, GitHub)](https://github.com/lechmazur/nyt-connections) |
| StealthMark (StealthMark Intelligence Benchmarks (overall score)) | 51.5 | 8 original tasks: Newton's Mirror, Ground Truth, Latch, Foresight, Mona Lisa, Selfie, Beach and Raccoon | Chained physical reasoning, planning without tools and precise visual construction | [StealthMark: The AI Benchmark Explained (Stealth Models)](https://stealthmodels.com/stealthmark) |

## Lifecycle and limitations log

Lifecycle events the source associates with this model.

No lifecycle event references this model. That is not evidence the model has no lifecycle plan — only that this source published none.

## What this profile does not claim

Values are reproduced exactly as their sources published them, in the units those sources declared; none are converted, interpolated, or averaged across providers. Any field marked unavailable was attempted and not returned. Last attempted fetch for this model's score: 2026-11-21 06:17 UTC.
