Best cell per row highlighted. Null means undisclosed — never counted as zero.
| Provider | xAI | xAI |
| Family / tier | Grok 4 · Reasoning | Grok Build · Coder |
| Status | GA | GA |
| Released | 2026-03-09 | 2026-05-19 |
| Knowledge cutoff | 2024-11 | 2024-11 |
| Context window | 1M | 256K |
| Max output tokens | — | 256K |
| Input modalities | text, image | text, image |
| Reasoning mode | optional | always |
| Open weights | No | No |
| Input | $1.25 | $1 |
| Output | $2.5 | $2 |
| Cached input | $0.2 | $0.2 |
| Batch input | — | — |
| Free tier | Yes | No |
| Output speed (tok/s) | 171.4 | — |
| Time to first token (s) | 13.24 | — |
| Latency tier | medium | slow |
| Trains on inputs | Yes | No |
| License | Proprietary | Proprietary |
| Clouds | — | — |
| Compliance | — | — |
| Unified score | 6.9 | 6.7 |
| Decision Maker | 7 | 7 |
| Domain Strategist | 6.5 | 7 |
| Finance Lead | 6.5 | 7.5 |
| Domain Practitioner | 7.5 | 7 |
| Power User | 6.5 | 6.5 |
| Skeptic | 6 | 6 |
| Value score | 7 | 7.5 |
| GPQA Diamond | 78.5 | — |
| MATH-500 | 87.3 | — |
| SWE-bench Verified | — | 70.8 |
| IFEval | 81 | — |
| TAU-bench | 93 | — |
| LMArena Elo | 1491 | — |
| Artificial Analysis Index | 49 | — |
Scores link to their sources. Missing cells mean the vendor hasn't disclosed a result — honesty over padding.