SpaceXAIGrok Build 0.1
Grok Build 0.1 is a SpaceXAI proprietary reasoning model, released 29 May 2026. Its best configuration ranks #241 of 785 on the BenchLeader Index at 54.8 ±5.3, in the upper half. The ± is the point: 307 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in knowledge (64) and lowest in agents & tools (41). At $1.25 per million tokens blended it is pricier than most ranked models. Output speed of 65 tokens per second puts it slower than most, with a first answer in 32.3 s. Last measured 16 Jun 2026.
- Blended price
- $1.25/M
- $1.00 in · $2.00 out
- Output speed
- 65 tok/s
- measured by Artificial Analysis
- First answer
- 32 s
- first token 1.37 s
- Context
- 256k
- Full answer
- 40 s
- median, reasoning included
- Cost per run
- –
- Released
- 29 May 2026
- Overall index55
- Reasoning56
- Coding54
- Agents & tools41
- Knowledge64
- Multimodal60
- Long context62
- Composite60
How its index has moved
9 Sept 2026 to 19 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source |
|---|---|---|
| LiveBench 1.0 Reasoningnot in index | 76.4%#59 | LiveBench |
| GPQA Diamond (AA)not in index | 89.5%#74 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 38.3%#100 | Artificial Analysis |
| CritPt | 9.1%#128 | Artificial Analysis |
Coding
| Benchmark | not stated | Source |
|---|---|---|
| SciCode | 50.2%#106 | SciCode |
| LiveBench 1.0 Codingnot in index | 65.4%#66 | LiveBench |
| Vibe Code Bench v1.1not in index | 13.3%#92 | Vals AI |
| Terminal-Bench 2.1 (AA)not in index | 52.1%#114 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source |
|---|---|---|
| LiveBench Agentic Codingnot in index | 45.8%#52 | LiveBench |
| τ³-Banking (AA) | 13.4%#126 | Artificial Analysis |
| GBAEvalnot in index | 2.4%#15 | Epoch AI Benchmarking Hub |
Maths
| Benchmark | not stated | Source |
|---|---|---|
| LiveBench Mathematicsnot in index | 78.4%#63 | LiveBench |
Knowledge
| Benchmark | not stated | Source |
|---|---|---|
| LiveBench 1.0 Data Analysisnot in index | 70.8%#48 | LiveBench |
| AA-Omniscience | 6.4#101 | Artificial Analysis |
| AA-Omniscience: accuracynot in index | 51.5%#56 | Artificial Analysis |
| AA-Omniscience: non-hallucinationnot in index | 6.9%#496 | Artificial Analysis |
Instruction following
| Benchmark | not stated | Source |
|---|---|---|
| LiveBench Languagenot in index | 72.5%#57 | LiveBench |
| LiveBench Instruction Followingnot in index | 65.2%#44 | LiveBench |
Multimodal
| Benchmark | not stated | Source |
|---|---|---|
| MMMU-Pro | 76.5%#87 | Artificial Analysis |
Long context
| Benchmark | not stated | Source |
|---|---|---|
| AA-LCR | 74.7%#159 | Artificial Analysis |
Composite
| Benchmark | not stated | Source |
|---|---|---|
| LiveBench 1.0not in index | 67.8%#60 | LiveBench |
| AA Intelligence Index v4.3.2 | 27.2#145 | Artificial Analysis |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| SpaceXAI | 78 tok/s | 1.42 s | $1.00 | $2.00 | 256k | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.200 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0010 | $0.0008 | 36.9 s |
| Summarize a 30-page report | 12,000 / 600 | $0.013 | $0.0060 | 41.5 s |
| Code edit | 6,000 / 1,500 | $0.0090 | $0.0054 | 55.3 s |
| Agentic coding session | 60,000 / 4,000 | $0.068 | $0.032 | 1.6 min |
| Structured extraction | 2,000 / 200 | $0.0024 | $0.0012 | 35.3 s |
More from SpaceXAI
See also
Questions people ask
- What are Grok Build 0.1's benchmark scores?
- As of 24 Oct 2026, Grok Build 0.1 scores 54.8 ±5.3 on the BenchLeader Index, strongest in knowledge (64) and weakest in agents & tools (41). That rests on 7 independent benchmark results, and every score on this page links to its publisher.
- How does Grok Build 0.1 rank?
- Grok Build 0.1 is #241 of 785 ranked configurations on 24 Oct 2026. 307 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does Grok Build 0.1 cost per 1M tokens?
- As of 24 Oct 2026, Grok Build 0.1 costs $1.00 per 1M input tokens and $2.00 per 1M output tokens, $1.25 blended (three input tokens per output token).
- When was Grok Build 0.1 released?
- SpaceXAI released Grok Build 0.1 on 29 May 2026.
Data as of 24 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Grok Build 0.1: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/grok-build-0-1.