# Grok 4.20

xAI · Proprietary · rank 62 · 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/grok-4-20-beta  
JSON: https://modelscale.dev/api/model/grok-4-20-beta

## Facts

| Field | Value | Evidence |
| --- | --- | --- |
| Canonical id | `grok-4-20-beta` | — |
| Overall score | 57.37 | Observed 2026-10-23 · source benchlm:models |
| Context window | 2M tokens | Observed 2026-10-23 · source benchlm:models |
| Release date | 2026-03-10 | Observed 2026-10-23 · source benchlm:models |
| Access type | Proprietary | — |
| Blended $/1M (75% input / 25% output) | $1.56 | 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.

| Axis | Score | Evidence |
| --- | --- | --- |
| Agentic | 32.1 | Observed 2026-10-23 · source benchlm:models |
| Coding | 49.3 | Observed 2026-10-23 · source benchlm:models |
| Knowledge | 59.2 | Observed 2026-10-23 · source benchlm:models |
| Reasoning | 44.9 | Observed 2026-10-23 · source benchlm:models |
| Multimodal & Grounded | 53.4 | Observed 2026-10-23 · source benchlm:models |
| Instruction Following | Unavailable | Unavailable · source benchlm:models |
| Math | 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 | 17.04 s | 2026-10-23 | 2026-10-23 | Observed 2026-10-23 · source benchlm:speed |
| Throughput | 108 tok/s | 2026-10-23 | 2026-10-23 | Observed 2026-10-23 · source benchlm:speed |

## Endpoint and price matrix

Every published price component, including cache reads and writes.

| Component | USD | Evidence |
| --- | --- | --- |
| Input / 1M tokens | $1.25 | Observed 2026-10-23 · source benchlm:pricing |
| Output / 1M tokens | $2.50 | Observed 2026-10-23 · source benchlm:pricing |
| Cache read / 1M tokens | $0.20 | Observed 2026-10-23 · source benchlm:pricing |
| Cache write / 1M tokens | Unavailable | Unavailable · source openrouter:pricing |
| Blended / 1M (75% input / 25% output) | $1.56 | Derived — from the input and output rates above; it has no source record of its own |
| Cost per successful task (LiveBench) | Unavailable | Fetch failed · source livebench:table |

**Self-hosted listing.** xAI's pricing page, read September 25, 2026, lists grok-4.20-0309-reasoning at $1.25 input / $0.20 cached input / $2.50 output per million tokens below 200K prompt tokens, with a 1M context window. Prompts of 200K tokens or more bill every token at $2.50 / $0.40 / $5.00. The grok-4.20-0309-non-reasoning variant lists at the same rates. BenchLM previously recorded $2.00 / $6.00 for this row. The rates above are a hosted price matched from another provider, not a first-party list price.

## 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 | $4.40 |
| Modelled tokens | 2.82M |

## Benchmark record

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

### Knowledge

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| GPQA-D (GPQA Diamond) | 88.5 | Graduate-level science questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |
| HealthBench Hard | 20.3 | 1,000 health prompts | Advanced health reasoning | [Muse Spark Eval Methodology](https://ai.meta.com/static-resource/muse-spark-eval-methodology) |
| MedXpertQA (Text) (MedXpertQA Text) | 50.2 | 2,450 medical multiple-choice questions | Professional medical knowledge | [Muse Spark Eval Methodology](https://ai.meta.com/static-resource/muse-spark-eval-methodology) |
| HLE w/o tools (Humanity's Last Exam without tools) | 31.6 | 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) | 88.6 | 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) | 86.3 | 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 |
| --- | --- | --- | --- | --- |
| SWE-bench Verified (Software Engineering Benchmark Verified) | 76.7 | 500 verified issues | Professional software engineering | [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://arxiv.org/abs/2310.06770) |
| LiveCodeBench Pro | 74.2 | Quarter-specific contest programming sets | High-end contest programming | [LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?](https://arxiv.org/abs/2506.11928) |
| SWE-bench Pro | 51.8 | 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) |
| Vibe Code Bench (Vibe Code Bench v1.1) | 4.06 | End-to-end web application builds | End-to-end software delivery | [Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development](https://www.vals.ai/benchmarks/vibe-code) |
| LiveCodeBench (Vals) (LiveCodeBench, Vals AI run) | 84.3 | 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) | 72.2 | Real repository issues by human time bucket | Frontier coding agents | [Vals AI SWE-bench, Vals AI run leaderboard](https://www.vals.ai/benchmarks/swebench) |

### Reasoning

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| ARC-AGI-2 (Abstraction and Reasoning Corpus for AGI v2) | 53.3 | 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) | 0.09 | 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) |

### Agentic

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Terminal-Bench 2.0 | 47.1 | Terminal-based software tasks | Professional software engineering | [Terminal-Bench 2.0](https://www.tbench.ai/) |
| Gert Labs (Gert Labs Composite Game Benchmark) | 38.36 | Novel game environments | Agentic coding and decision-making | [Gert Labs rankings](https://gertlabs.com/rankings) |
| DeepSearchQA | 62.8 | Agentic browsing and list-answer questions | Agentic web research | [Muse Spark Eval Methodology](https://ai.meta.com/static-resource/muse-spark-eval-methodology) |
| Terminal-Bench 2.1 (Vals) (Terminal-Bench 2.1, Vals AI run) | 44.2 | 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) |

### Multimodal & Grounded

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| MMMU-Pro (Massive Multi-discipline Multimodal Understanding Pro) | 75.2 | Multimodal academic reasoning | Frontier multimodal | [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://arxiv.org/abs/2409.02813) |
| Design Arena Website (Design Arena Website Elo) | 1231 | Website generation comparisons | Design and website generation | [OpenRouter Grok 4.3 benchmarks](https://openrouter.ai/x-ai/grok-4.3/benchmarks) |
| ERQA | 54.1 | Evidence-based visual QA | Grounded multimodal reasoning | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |
| MedXpertQA (MM) (MedXpertQA Multimodal) | 65.8 | 2,000 multimodal medical questions | Clinical multimodal reasoning | [Muse Spark Eval Methodology](https://ai.meta.com/static-resource/muse-spark-eval-methodology) |
| SimpleVQA | 57.4 | Visual QA tasks | General visual understanding | [GLM-5V-Turbo](https://docs.z.ai/guides/vlm/glm-5v-turbo) |
| CharXiv (CharXiv Reasoning) | 60.9 | Scientific chart reasoning | Scientific visualization reasoning | [CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs](https://charxiv.github.io/) |

## 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: 2026-10-23 13:17 UTC.