xAIGrok Build 0.1
Best configuration ranks #165 of 610 on the BenchLeader Index at 56.1 ±10.1. Last measured 25 Jun 2026. Released 29 May 2026.
- Blended price
- $1.25/M
- $1.00 in · $2.00 out
- Output speed
- 62 tok/s
- First answer
- 33 s
- first token 0.80 s
- Context
- 256k
- Overall index56
- Coding58
- Knowledge67
- Multimodal61
- Long context64
- Composite46
Benchmark results
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 | default | Source |
|---|---|---|
| LiveBench Reasoningnot in index | 76.4%#45 | LiveBench |
| GPQA Diamond (AA)not in index | 89.5%#74 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 38.3%#65 | Artificial Analysis |
Coding
| Benchmark | default | Source |
|---|---|---|
| SciCode | 50.2%#57 | SciCode |
| LiveBench Codingnot in index | 65.4%#52 | LiveBench |
Agents & tools
| Benchmark | default | Source |
|---|---|---|
| LiveBench Agentic Codingnot in index | 45.8%#39 | LiveBench |
Maths
| Benchmark | default | Source |
|---|---|---|
| LiveBench Mathematicsnot in index | 78.4%#49 | LiveBench |
Knowledge
| Benchmark | default | Source |
|---|---|---|
| LiveBench Data Analysisnot in index | 70.8%#36 | LiveBench |
| AA-Omniscience | 6.4#68 | Artificial Analysis |
Instruction following
| Benchmark | default | Source |
|---|---|---|
| LiveBench Languagenot in index | 72.5%#46 | LiveBench |
Multimodal
| Benchmark | default | Source |
|---|---|---|
| MMMU-Pro | 76.5%#62 | Artificial Analysis |
Long context
| Benchmark | default | Source |
|---|---|---|
| AA-LCR | 74.7%#114 | Artificial Analysis |
Composite
| Benchmark | default | Source |
|---|---|---|
| LiveBench | 67.8%#46 | LiveBench |
| AA Intelligence Index | 27.2#99 | 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 | 90 tok/s | 0.80 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 | 37.9 s |
| Summarise a 30-page report | 12,000 / 600 | $0.013 | $0.0060 | 42.7 s |
| Code edit | 6,000 / 1,500 | $0.0090 | $0.0054 | 57.3 s |
| Agentic coding session | 60,000 / 4,000 | $0.068 | $0.032 | 1.6 min |
| Structured extraction | 2,000 / 200 | $0.0024 | $0.0012 | 36.2 s |
See also
Data as of 9 Sept 2026. Compare with another model.