# GPT-6.2 Astra

OpenAI · Proprietary · rank 2 · 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-6-2-astra  
JSON: https://modelscale.dev/api/model/gpt-6-2-astra

## Facts

| Field | Value | Evidence |
| --- | --- | --- |
| Canonical id | `gpt-6-2-astra` | — |
| Overall score | 91 | Observed 2026-11-21 · source benchlm:models |
| Verified score (BenchLM): a separate BenchLM figure, not the overall score | 82 | Observed 2026-11-21 · source benchlm:models |
| Context window | 1.05M tokens | Observed 2026-11-21 · source benchlm:models |
| Modalities (models.dev) | Input: text, file, image · Output: text | Observed 2026-11-21 · source openrouter:pricing |
| Release date | 2026-11-17 | Observed 2026-11-21 · source benchlm:models |
| Access type | Proprietary | — |
| Blended $/1M (75% input / 25% output) | $16.00 | 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 | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Coding | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Knowledge | 84.9 | Observed 2026-11-21 · source benchlm:models | 84.9 | Observed 2026-11-21 · source benchlm:models |
| Reasoning | 91.4 | Observed 2026-11-21 · source benchlm:models | 91.4 | Observed 2026-11-21 · source benchlm:models |
| Multimodal & Grounded | 87.8 | Observed 2026-11-21 · source benchlm:models | 87.8 | Observed 2026-11-21 · source benchlm:models |
| Instruction Following | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Math | 93.8 | Observed 2026-11-21 · source benchlm:models | 93.8 | 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 | 50 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 | $8.00 | Observed 2026-11-21 · source benchlm:pricing |
| Output / 1M tokens | $40.00 | Observed 2026-11-21 · source benchlm:pricing |
| Cache read / 1M tokens | $0.40 | Observed 2026-11-21 · source benchlm:pricing |
| Cache write / 1M tokens | $10.00 | Observed 2026-11-21 · source openrouter:pricing |
| Blended / 1M (75% input / 25% output) | $16.00 | 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) | $4.00 | Observed 2026-11-21 · source openrouter:pricing |
| Batch output / 1M tokens (OpenRouter batch) (base rate) | $20.00 | Observed 2026-11-21 · source openrouter:pricing |
| Batch cache read / 1M tokens (OpenRouter batch) (base rate) | $0.20 | Observed 2026-11-21 · source openrouter:pricing |
| Batch cache write / 1M tokens (OpenRouter batch) (base rate) | $5.00 | Observed 2026-11-21 · source openrouter:pricing |

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

### 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 | $8.00 input / $30.00 output per 1M · cache read $0.40 · cache write $10.00 | Observed 2026-11-21 · source openrouter:pricing |

**Pricing note.** OpenAI's GPT-6.2 Astra model page lists $8.00 input / $0.40 cached input / $10.00 cache writes (30-minute retention; $20 for 12-hour retention) / $40.00 output per million tokens, 20% below GPT-6 Astra's input and output rates. Requests above 272K input tokens are charged at 2x input and cache rates and 1.5x output for the full request; Batch is 50% of Standard, Fast mode is 2x, and Ultrafast is 3x through February 28, 2027 and 6x from March 1, 2027. A Responses API background-completion beta cuts token rates by 30% (two-hour window) or 40% (eight-hour window).

## 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 | $45.06 |
| Modelled tokens | 2.82M |

## Benchmark record

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

### Knowledge

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| HealthBench Professional (raw) (HealthBench Professional raw score) | 66.0 | 525 physician-authored conversations | Professional clinical tasks | [HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats](https://arxiv.org/abs/2604.27470) |
| GPQA (Graduate-Level Google-Proof Q&A) | 97 | 448 questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |
| GPQA-D (GPQA Diamond) | 97.0 | Graduate-level science questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |
| Artificial Analysis Intelligence Index | 62.1 | Cross-benchmark intelligence index | Display-only external reference | [Artificial Analysis](https://artificialanalysis.ai/) |
| AA-Omniscience Index (Artificial Analysis Omniscience Index) | 50.0 | Knowledge questions | Broad factual knowledge | [AA-Omniscience: Knowledge and Hallucination Benchmark](https://artificialanalysis.ai/evaluations/omniscience) |
| AA-Omniscience Accuracy (Artificial Analysis Omniscience Accuracy) | 68.6 | Knowledge questions | Broad knowledge | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA-Omniscience Hallucination Rate (Artificial Analysis Omniscience Hallucination Rate) | 59.1 | Knowledge questions | Factuality | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| HealthBench Professional | 66.3 | Clinician chat tasks | Professional clinical workflows | [HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats](https://arxiv.org/abs/2604.27470) |

### Coding

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Bug Hunt Bench | 62.7 | 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) |
| FrontierCode 2.0 | 44.2 | 132 private software-engineering tasks | Frontier coding-agent quality | [FrontierCode 2.0](https://cognition.com/blog/frontier-code-2.0) |

### Mathematics

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| FrontierMath v2 (Tiers 1-3) (FrontierMath v2 Tiers 1-3) | 92.632 | 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) | 100.000 | 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) | 98.50 | 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) | 95.833333 | 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) | 70.306138 | 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) |
| MLCR-AA (Medical Long Context Reasoning (MLCR-AA)) | 39.4 | Long, fragmented medical-record reasoning | Long-context medical reasoning | [Medical Long Context Reasoning (MLCR-AA)](https://artificialanalysis.ai/evaluations/mlcr-aa) |
| ARC-AGI-3 Provider Adapter (ARC-AGI-3 Semi-Private: Provider Adapter harness) | 99.80 | — | — | [ARC Prize verified ARC-AGI-3 results](https://arcprize.org/leaderboard) |

### Agentic

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Terminal-Bench-Science 0.1 | 77.1 | 70 expert-curated scientific research workflows | Frontier scientific research workflows | [Terminal-Bench-Science 0.1](https://www.terminal-bench-science.ai/) |
| AA Briefcase (Artificial Analysis Briefcase) | 1643 | Professional knowledge-work tasks | Professional work | [Artificial Analysis Briefcase Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/aa-briefcase) |
| AA AutomationBench (Artificial Analysis AutomationBench) | 77.2 | Business-process automation tasks | Agentic automation | [Artificial Analysis AutomationBench Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/automationbench-aa) |
| AA EnterpriseOps-Gym (Artificial Analysis EnterpriseOps-Gym) | 29.9 | Enterprise operations workflows | Enterprise agent operations | [Artificial Analysis EnterpriseOps-Gym Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa) |
| AA Terminal-Bench 4.0 (Artificial Analysis Terminal-Bench v4.0) | 64.1 | 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) | 29.8 | Professional document-production tasks | Professional knowledge work | [GDP.pdf Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/gdp-pdf) |
| AA-AnalystAgent (Artificial Analysis AnalystAgent) | 62.5 | Spreadsheet and document analysis questions | Business and data analysis | [AA-AnalystAgent Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/aa-analyst-agent) |
| Harvey LAB-AA v1.1 | 15.0 | 120 private legal tasks across 24 practice areas | Professional legal work | [Harvey LAB-AA v1.1 Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/harvey-lab-aa) |
| MazeBench (MazeBench: visual spatial reasoning in a 3D open world) | 17 | 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 | 62.10 | 66 professional computer-work tasks | Frontier autonomous knowledge work | [Terminal-Bench 4.1](https://www.tbench.ai/news/terminal-bench-4-1) |
| AA Cyber Index (Artificial Analysis Cyber Index) | 37.3 | 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) | 65.0 | 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) | 46.8 | 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) |
| MKA (Multimodal Knowledge Agent Benchmark) | 52.7 | 200 multimodal professional tasks across 10 industry verticals | Expert multimodal knowledge work | [MKA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/mka) |
| LifeVal (LifeVal: everyday life tasks) | 86.1 | 169 everyday life tasks (caregiving, health, education, household administration, personal finance, shopping, government services) | Agentic personal-assistant work | [LifeVal](https://openai.com/index/lifeval/) |

### Multimodal & Grounded

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AA-MMMU-Pro (Artificial Analysis MMMU-Pro) | 89.5 | Multimodal academic reasoning | Frontier multimodal | [Artificial Analysis MMMU-Pro Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/mmmu-pro) |

### external

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| ExploitBench (ExploitBench v8-bench) | 100 | V8 exploit synthesis runs | Browser exploitation and cybersecurity | [ExploitBench](https://exploitbench.ai/) |
| SEC-Bench Pro | 86.8 | Security engineering tasks | Advanced cybersecurity | [Introducing GPT-5.6](https://openai.com/index/gpt-5-6/) |
| FrontierCyber | 31.3 | 197 dynamic cyber tasks | Easy through elite cyber operations | [FrontierCyber](https://www.irregular.com/research/frontiercyber) |
| CyScenarioBench success (CyScenarioBench Average Success Rate) | 63 | 11 cyber scenarios | Long-horizon cybersecurity | [Assessing GPT-5.6 Sol](https://www.irregular.com/research/assessing-gpt-5.6-sol) |
| CyScenarioBench solved (CyScenarioBench Scenarios Ever Solved) | 9 | 11 cyber scenarios | Long-horizon cybersecurity | [Assessing GPT-5.6 Sol](https://www.irregular.com/research/assessing-gpt-5.6-sol) |
| SpireClimb (SpireClimb (Slay the Spire 1 and 2)) | 41.3 | 60 Slay the Spire 1 runs (Ascension 20, Heart kill) and 75 Slay the Spire 2 runs (Ascension 10) per model | Maximum game difficulty, long-horizon computer use | [SpireClimb (Epoch AI)](https://epoch.ai/benchmarks/spireclimb) |
| Chess Puzzles (Chess Puzzles (Epoch AI)) | 78.0 | 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)) | 95.0 | 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)) | 89.2 | 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) |
| EBR-bench (Earthborne Rangers (EBR-bench)) | 92.4 | Ten playthroughs of an Earthborne Rangers campaign segment per sample (eight learning, two scored) | Learning an unfamiliar game over multi-hour playthroughs | [Earthborne Rangers (EBR-bench), Epoch AI](https://epoch.ai/benchmarks/ebr-bench) |
| MirrorCode (MirrorCode (Epoch AI and METR)) | 67.8 | 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) |
| ExploitBench Internal Port (ExploitBench — Internal Port (June–August 2026)) | 53.5 | Recently disclosed V8 and Chrome vulnerabilities (June–August 2026) | Browser exploitation | [GPT-6 Cyber System Card](https://deploymentsafety.openai.com/gpt-6-cyber) |
| ExploitGym Honeypot (ExploitGym Honeypot out-of-scope exploitation rate) | 0.00 | Hard ExploitGym tasks with an out-of-scope honeypot service | Cyber-agent scope adherence | [GPT-6 Cyber: Advancing the frontier of aligned cybersecurity agents](https://openai.com/index/introducing-gpt-6-cyber/) |

## 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 | max | 0.9684 | fraction (0–1) | 2026-10-27 | Last good 2026-11-20 · source epoch:benchmarks |
| FrontierMath Tiers 1-3 (v2) | max | 0.9263 | fraction (0–1) | 2026-10-27 | Last good 2026-11-20 · source epoch:benchmarks |
| FrontierMath Tier 4 (v2) | max | 1 | fraction (0–1) | 2026-10-27 | Last good 2026-11-20 · source epoch:benchmarks |
| SimpleQA Verified | max | 0.785 | fraction (0–1) | 2026-10-27 | 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.
