# GPT-5.6 Terra

OpenAI · Proprietary · rank 34 · bench-align-v5

> 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://modelscale.dev/models/gpt-5-6-terra  
JSON: https://modelscale.dev/api/model/gpt-5-6-terra

## Facts

| Field | Value | Evidence |
| --- | --- | --- |
| Canonical id | `gpt-5-6-terra` | — |
| Overall score | 65.9 | 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 | 1.05M tokens | Observed 2026-11-21 · source benchlm:models |
| Max output (models.dev) | 128,000 tokens | Observed 2026-11-21 · source modelsdev:catalog |
| Modalities (models.dev) | Input: text, image, PDF · Output: text | Observed 2026-11-21 · source modelsdev:catalog |
| Release date | 2026-07-09 | Observed 2026-11-21 · source benchlm:models |
| Access type | Proprietary | — |
| Blended $/1M (75% input / 25% output) | $4.50 | 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 | 75.9 | Observed 2026-11-21 · source benchlm:models | 72.4 | Observed 2026-11-21 · source benchlm:models |
| Coding | 65.3 | Observed 2026-11-21 · source benchlm:models | 64.5 | Observed 2026-11-21 · source benchlm:models |
| Knowledge | 74.5 | Observed 2026-11-21 · source benchlm:models | 74.6 | Observed 2026-11-21 · source benchlm:models |
| Reasoning | 67.4 | Observed 2026-11-21 · source benchlm:models | 66.6 | Observed 2026-11-21 · source benchlm:models |
| Multimodal & Grounded | 84.1 | Observed 2026-11-21 · source benchlm:models | 84.1 | Observed 2026-11-21 · source benchlm:models |
| Instruction Following | 86.9 | Observed 2026-11-21 · source benchlm:models | 86.9 | Observed 2026-11-21 · source benchlm:models |
| Math | 83.1 | Observed 2026-11-21 · source benchlm:models | 83.1 | Observed 2026-11-21 · 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 | Unavailable | Unavailable | Unavailable | Unavailable · source benchlm:speed |
| Throughput | 67 tok/s | 2026-11-21 | 2026-11-21 | Observed 2026-11-21 · source openrouter:endpoints |

## Endpoint and price matrix

Every published price component, including cache reads and writes.

| Component | USD | Evidence |
| --- | --- | --- |
| Input / 1M tokens (base rate) | $2.00 | Observed 2026-11-21 · source benchlm:pricing |
| Output / 1M tokens (base rate) | $12.00 | Observed 2026-11-21 · source benchlm:pricing |
| Cache read / 1M tokens (base rate) | $0.20 | Observed 2026-11-21 · source benchlm:pricing |
| Cache write / 1M tokens (base rate) | $2.50 | Observed 2026-11-21 · source openrouter:pricing |
| Blended / 1M (75% input / 25% output) | $4.50 | 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 |
| Batch input / 1M tokens (OpenRouter batch) (base rate) | $1.00 | Observed 2026-11-21 · source openrouter:pricing |
| Batch output / 1M tokens (OpenRouter batch) (base rate) | $6.00 | Observed 2026-11-21 · source openrouter:pricing |
| Batch cache read / 1M tokens (OpenRouter batch) (base rate) | $0.10 | Observed 2026-11-21 · source openrouter:pricing |

Batch API rate (asynchronous jobs), from OpenRouter's batch listing.

### Long-context price tiers (models.dev)

The standard input, output and cache rates above are the base rate. models.dev publishes higher rates for requests whose prompt exceeds the thresholds below. The batch rates have their own long-context tiers, from OpenRouter's batch listing, shown separately. The cost simulator prices a standard-rate request whose whole prompt is above a threshold entirely at the highest of these tiers it exceeds, and a batch request only at a batch tier; it never applies these tiers to batch rates. The cost example on this page uses the base rate: its 1,200-token prompt is below every threshold.

| Prompt size | USD per 1M tokens | Evidence |
| --- | --- | --- |
| Above 272K prompt tokens | $4.00 input / $18.00 output per 1M · cache read $0.40 · cache write $5.00 | Observed 2026-11-21 · source modelsdev:catalog |

### Long-context batch price tiers (OpenRouter batch)

The batch rates above are the base batch rate. OpenRouter's batch listing, the same listing as those rates, publishes higher batch rates for requests whose total prompt is above the thresholds below. The cost simulator prices a batch request whose whole prompt is above a threshold entirely at the highest batch tier it exceeds.

| Prompt size | Batch USD per 1M tokens | Evidence |
| --- | --- | --- |
| Above 272K prompt tokens | $2.00 input / $9.00 output per 1M · cache read $0.20 | Observed 2026-11-21 · source openrouter:pricing |

**Pricing note.** OpenAI's API pricing page lists GPT-5.6 Terra at $2.00 input / $0.20 cached input / $12.00 output per million tokens for short-context requests. Prompts above 272K input tokens use the published $4.00 input / $0.40 cached input / $18.00 output long-context tier; cache writes cost $2.50 per million tokens. Observed September 11, 2026; the $2.50 / $15.00 launch rate is retained in the price history.

## 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 | $12.67 |
| Modelled tokens | 2.82M |

## Benchmark record

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

### Knowledge

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| GPQA (Graduate-Level Google-Proof Q&A) | 92.9 | 448 questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |
| GPQA-D (GPQA Diamond) | 92.9 | Graduate-level science questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |
| HLE-Verified | 51.1 | 1,811 verified or revised expert questions | Frontier multidisciplinary expert reasoning | [HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam](https://arxiv.org/abs/2602.13964) |
| LABBench2 (LABBench2: An Improved Benchmark for AI Systems Performing Biology Research) | 81.2 | Nearly 1,900 biology-research tasks | Real-world biology research | [LABBench2: An Improved Benchmark for AI Systems Performing Biology Research](https://arxiv.org/abs/2604.09554) |
| Artificial Analysis Intelligence Index | 55.0 | Cross-benchmark intelligence index | Display-only external reference | [Artificial Analysis](https://artificialanalysis.ai/) |
| AA-GPQA Diamond (Artificial Analysis GPQA Diamond) | 92.5 | 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) | 42.9 | 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) | 0.1 | Knowledge questions | Broad factual knowledge | [AA-Omniscience: Knowledge and Hallucination Benchmark](https://artificialanalysis.ai/evaluations/omniscience) |
| AA-Omniscience Accuracy (Artificial Analysis Omniscience Accuracy) | 46.8 | Knowledge questions | Broad knowledge | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA-Omniscience Hallucination Rate (Artificial Analysis Omniscience Hallucination Rate) | 87.9 | Knowledge questions | Factuality | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| HealthBench Hard | 32.7 | 1,000 health prompts | Advanced health reasoning | [Muse Spark Eval Methodology](https://ai.meta.com/static-resource/muse-spark-eval-methodology) |
| HealthBench Professional | 57.7 | Clinician chat tasks | Professional clinical workflows | [HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats](https://arxiv.org/abs/2604.27470) |
| GPQA Diamond (Vals) (GPQA Diamond, Vals AI run) | 90.9 | 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) | 86.7 | 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 | 87.4 | Terminal-based software-agent tasks | Professional software engineering | [Terminal-Bench](https://www.tbench.ai/) |
| Terminal-Bench 2.0 | 87.4 | Terminal-based software tasks | Professional software engineering | [Terminal-Bench 2.0](https://www.tbench.ai/) |
| SWE-bench Pro | 63.4 | 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 | 87.0 | 23 post-cutoff repository tasks in the v3 report | Professional multi-file software engineering | [VulcanBench](https://github.com/morganlinton/VulcanBench/tree/main) |
| FrontierCode 1.1 Extended | 55.8 | 150 private software-engineering tasks | Frontier coding-agent quality | [FrontierCode leaderboard](https://cognition.com/frontiercode) |
| AA Coding Index (Artificial Analysis Coding Index) | 76.7 | Cross-benchmark coding index | Display-only external reference | [Artificial Analysis model leaderboards](https://artificialanalysis.ai/leaderboards/models) |
| AA-SciCode (Artificial Analysis SciCode) | 55.0 | Scientific coding subproblems | Scientific programming | [Artificial Analysis SciCode Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/scicode) |
| LiveCodeBench (Vals) (LiveCodeBench, Vals AI run) | 85.9 | 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) | 95.4 | 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 | 69.6 | 113 software engineering tasks across 91 repositories and 5 languages | Long-horizon software engineering | [DeepSWE benchmark blog](https://deepswe.datacurve.ai/blog) |
| VulcanBench Frontier v4 | 89.0 | 23 behavioural-reconstruction coding tasks | Professional multi-file software engineering | [VulcanBench Frontier v4 leaderboard](https://vulcanbench.com/leaderboard.html) |

### Mathematics

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| FrontierMath (legacy) (FrontierMath legacy aggregate) | 84.9 | Historical aggregate | Research-level mathematics | [FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI](https://epoch.ai/frontiermath) |
| FrontierMath v2 (Tiers 1-3) (FrontierMath v2 Tiers 1-3) | 84.900 | 285 private advanced mathematics problems | From olympiad-plus to early research mathematics | [FrontierMath v2 benchmark hub](https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2) |
| FrontierMath v2 (Tier 4) (FrontierMath v2 Tier 4) | 68.300 | 41 private extreme-difficulty mathematics problems | Research-level mathematics requiring hours or days of expert work | [FrontierMath Tier 4 v2 leaderboard](https://epoch.ai/benchmarks/frontiermath-tier-4-v2?view=graph&tab=leaderboard) |

### Reasoning

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| ARC-AGI-1 (ARC-AGI-1 Semi-Private Evaluation) | 96.50 | Semi-private ARC-AGI-1 evaluation set | Abstract visual reasoning | [ARC Prize leaderboard](https://arcprize.org/) |
| ARC-AGI-2 (Abstraction and Reasoning Corpus for AGI v2) | 83.9 | Visual pattern completion and abstract reasoning | Expert-level — hardest public reasoning benchmark | [ARC-AGI-2: A Harder General Intelligence Benchmark](https://arcprize.org/arc-agi/2/) |
| ARC-AGI-3 (Abstraction and Reasoning Corpus for AGI v3) | 0.8 | Interactive game-like tasks with hidden rules | Frontier agentic reasoning | [ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence](https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf) |
| AA-LCR (Artificial Analysis Long Context Reasoning) | 83.0 | 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)) | 31.7 | 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) | 30.0 | Research-level physics questions | Research-level physics reasoning | [CritPt Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/critpt) |

### Instruction Following

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AA-IFBench (Artificial Analysis IFBench) | 71.2 | Verifiable instruction constraints | Instruction precision | [Artificial Analysis IFBench Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/ifbench) |

### Agentic

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Terminal-Bench 3.0 | 20.8 | 74 professional computer-work tasks across 7 domains | Frontier autonomous knowledge work | [Terminal-Bench 3.0](https://www.frontierbench.ai/) |
| AA Briefcase (Artificial Analysis Briefcase) | 1330 | Professional knowledge-work tasks | Professional work | [Artificial Analysis Briefcase Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/aa-briefcase) |
| AA AutomationBench (Artificial Analysis AutomationBench) | 59.6 | Business-process automation tasks | Agentic automation | [Artificial Analysis AutomationBench Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/automationbench-aa) |
| AA EnterpriseOps-Gym (Artificial Analysis EnterpriseOps-Gym) | 38.5 | Enterprise operations workflows | Enterprise agent operations | [Artificial Analysis EnterpriseOps-Gym Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa) |
| AA Harvey LAB v1.0 (Artificial Analysis Harvey LAB-AA v1.0) | 85.2 | Legal agent tasks | Professional legal work | [Artificial Analysis Harvey LAB-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/harvey-lab-aa) |
| AA ITBench (Artificial Analysis ITBench-AA) | 51.0 | IT incident-response tasks | Enterprise IT operations | [Artificial Analysis ITBench-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/itbench-aa) |
| AA Tau3 Banking (Artificial Analysis Tau3-Banking) | 40.2 | Banking tool-use workflows | Agentic banking workflows | [Artificial Analysis Tau3-Banking Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/tau3-banking) |
| Terminal-Bench 2.0 | 87.4 | Terminal-based software tasks | Professional software engineering | [Terminal-Bench 2.0](https://www.tbench.ai/) |
| Terminal-Bench 2.1 | 87.4 | Terminal-based software-agent tasks | Professional software engineering | [Terminal-Bench](https://www.tbench.ai/) |
| BrowseComp | 87.5 | Research questions requiring browsing | Hard web research | [BrowseComp](https://openai.com/index/browsecomp/) |
| GDPval-AA | 1583 | 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) | 47.6 | Economically valuable tasks | Professional agentic workflows | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA Agentic Index (Artificial Analysis Agentic Index) | 43.7 | 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) | 35.4 | 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) | 24.0 | Professional document-production tasks | Professional knowledge work | [GDP.pdf Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/gdp-pdf) |
| APEX-Agents-AA | 38.9 | 452 professional-services agent tasks | Long-horizon workplace agent tasks | [APEX-Agents-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/apex-agents-aa) |
| OSWorld 2.0 | 50.2 | 108 long-horizon computer-use workflows | Long-horizon professional workflows | [OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks](https://arxiv.org/abs/2606.29537) |
| CyberGym | 81.8 | 1,507 vulnerability analysis instances | Real-world cybersecurity | [CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale](https://www.cybergym.io/) |
| ExploitGym | 23.2 | 898 exploitation tasks | Advanced cybersecurity exploitation | [ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?](https://arxiv.org/abs/2605.11086) |
| Toolathlon | 53.1 | Multi-tool workflows | Advanced tool use | [Introducing GPT-5.4 mini and nano](https://openai.com/index/introducing-gpt-5-4-mini-and-nano/) |
| τ²-bench results (τ²-Bench Tool-Agent-User Evaluation) | 86.3 | Airline, retail, and telecom customer-service task sets | Dual-control customer-service workflows | [τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://arxiv.org/abs/2506.07982) |
| Terminal-Bench 2.1 (Vals) (Terminal-Bench 2.1, Vals AI run) | 77.5 | Difficult terminal tasks | Frontier agentic | [Vals AI Terminal-Bench 2.1, Vals AI run leaderboard](https://www.vals.ai/benchmarks/terminal-bench-2-1) |
| ApprenticeBench (ApprenticeBench: end-to-end computer use, continual learning, and long-horizon agency on a real accounts-payable job) | 16 | 100 vendor bills processed in sequence inside a simulated construction company | Long-horizon computer use with offline and online continual learning | [ApprenticeBench: a step change in AI's job readiness](https://neocognition.io/blog/apprentice-bench/) |
| MazeBench (MazeBench: visual spatial reasoning in a 3D open world) | 6 | 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) |
| Terminal-Bench 4.1 | 21.50 | 66 professional computer-work tasks | Frontier autonomous knowledge work | [Terminal-Bench 4.1](https://www.tbench.ai/news/terminal-bench-4-1) |
| DeepsecBench-AA (Artificial Analysis DeepsecBench-AA) | 25.1 | Vulnerability discovery in real codebases | Security code review | [DeepsecBench-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/deepsecbench-aa) |

### Multimodal & Grounded

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| MMMU-Pro (Massive Multi-discipline Multimodal Understanding Pro) | 80.7 | Multimodal academic reasoning | Frontier multimodal | [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://arxiv.org/abs/2409.02813) |
| AA-MMMU-Pro (Artificial Analysis MMMU-Pro) | 80.7 | Multimodal academic reasoning | Frontier multimodal | [Artificial Analysis MMMU-Pro Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/mmmu-pro) |
| MMMU-Pro w/ Python (MMMU-Pro with Python) | 82 | Multimodal academic reasoning | Frontier multimodal | [Introducing GPT-5.4 mini and nano](https://openai.com/index/introducing-gpt-5-4-mini-and-nano/) |
| ParseBench-1 (ParseBench-1: document parsing for AI agents (LlamaIndex leaderboard, first release)) | 67.06 | 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)) | 92.26 | 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)) | 78.14 | 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 |
| --- | --- | --- | --- | --- |
| ExploitBench (ExploitBench v8-bench) | 53 | V8 exploit synthesis runs | Browser exploitation and cybersecurity | [ExploitBench](https://exploitbench.ai/) |
| Chess Puzzles (Chess Puzzles (Epoch AI)) | 47.0 | 100 programmatically generated chess positions with a single best move | Novel chess positions, single best move | [Chess Puzzles (Epoch AI)](https://epoch.ai/benchmarks/chess-puzzles) |
| Mystery Game Puzzles (Mystery Game Puzzles (Epoch AI)) | 35.0 | 100 single-best-move positions from an undisclosed game | Unfamiliar game positions, single best move | [Mystery Game Puzzles (Epoch AI)](https://epoch.ai/benchmarks/mystery-game-puzzles) |
| Furniture Assembly (Furniture Assembly Benchmark (Epoch AI)) | 54.2 | 60 photos of three IKEA builds, some with deliberate assembly mistakes | Spatial reasoning from technical diagrams to real photos | [Furniture Assembly Benchmark (Epoch AI)](https://epoch.ai/benchmarks/furniture-assembly) |
| MirrorCode (MirrorCode (Epoch AI and METR)) | 41.1 | 30 reimplementation tasks (15 programs in two languages), three attempts each | Days-long software engineering without source code | [MirrorCode (Epoch AI)](https://epoch.ai/benchmarks/mirrorcode) |
| FACTS Multimodal | 39.9 | About 1,500 image questions: 711 public and 811 held out | Image-grounded factual answering | [BenchLM](https://benchlm.ai/benchmarks/facts-multimodal) |
| DAYJOB | 2.8 | 130 long-horizon tasks: 80 finance and 50 healthcare | Long-horizon professional work | [BenchLM](https://benchlm.ai/benchmarks/dayjob) |
| DAYJOB Healthcare | 2.0 | 50 long-horizon healthcare tasks across five subfields | Long-horizon clinical and healthcare operations work | [BenchLM](https://benchlm.ai/benchmarks/dayjob-healthcare) |
| Joke Arena | 1478 | 100 joke prompts in 10 categories, rated by human votes | Humour writing | [BenchLM](https://benchlm.ai/benchmarks/joke-arena) |
| Pelican Arena | 1334 | One prompt: an animated SVG of a pelican riding a bicycle, rated by human votes | Vector drawing and animation in code | [BenchLM](https://benchlm.ai/benchmarks/pelican-arena) |
| ASCII Arena | 1290 | ASCII drawings of subjects from Google's Quick, Draw! dataset, rated by human votes | Text-character drawing | [BenchLM](https://benchlm.ai/benchmarks/ascii-arena) |
| Game Arena Go | 512 | Head-to-head Go games on a 13 x 13 board | Strategic planning and rule-following | [BenchLM](https://benchlm.ai/benchmarks/game-arena-go) |
| BabaIsBench (BabaIsBench (Baba Is You intro levels, pass@1)) | 88 | 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)) | 78.4 | 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)) | 45.8 | 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) |
| FrontierPhysics (End-to-End Physics Research Benchmark for AI Agents) | 3.6 | 56 research projects from 42 physicists across nine fields, three trials each (168 rollouts per setup) | Open-ended research projects that took their authors about 270 days on average | [FrontierPhysics: Evaluating Agents for End-to-End Physics Research (arXiv, November 4, 2026)](https://arxiv.org/abs/2611.06910) |

## Independent scores (Epoch AI)

A second, independent score source: Epoch's own figures in Epoch's units, one line per model version Epoch evaluated (effort setting as Epoch labels it); higher is better. Not part of this site's capability scores or rank.

| Benchmark | Variant | Score | Unit | Epoch date | Evidence |
| --- | --- | --- | --- | --- | --- |
| GPQA Diamond | low | 0.8737 | fraction (0–1) | 2026-08-07 | Last good 2026-11-20 · source epoch:benchmarks |
| GPQA Diamond | max | 0.9331 | fraction (0–1) | 2026-07-09 | Last good 2026-11-20 · source epoch:benchmarks |
| GPQA Diamond | none | 0.7727 | fraction (0–1) | 2026-08-07 | Last good 2026-11-20 · source epoch:benchmarks |
| FrontierMath Tiers 1-3 (v2) | max | 0.8596 | fraction (0–1) | 2026-07-09 | Last good 2026-11-20 · source epoch:benchmarks |
| FrontierMath Tier 4 (v2) | max | 0.7073 | fraction (0–1) | 2026-07-09 | Last good 2026-11-20 · source epoch:benchmarks |
| SimpleQA Verified | max | 0.432 | fraction (0–1) | 2026-08-10 | Last good 2026-11-20 · source epoch:benchmarks |

Source: [Epoch AI, CC BY 4.0](https://epoch.ai/benchmarks) ([licence](https://creativecommons.org/licenses/by/4.0/)). Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from https://epoch.ai/benchmarks.

## 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 01:17 UTC.
