Grok 4.3 vs Grok Build 0.1
| Spec | Grok 4.3 | Grok Build 0.1 |
|---|---|---|
| Respan Index | 22.2 (#118) | 20.8 (#124) |
| Blended price per 1M | $1.56 | $1.25 |
| Context window | 1M | 256K |
| Input / output per 1M | $1.25 / $2.5 | $1 / $2 |
| Max output | - | - |
| Input | text, vision | text |
| Released | - | 2026-05-19 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | Grok 4.3 | Grok Build 0.1 |
|---|---|---|
| Coding | 5.2 Grok 4.3 | 4.5 Grok Build 0.1 |
| Agents | 4.2 Grok 4.3 | 13.7* Grok Build 0.1 |
| Reasoning | 36.2 Grok 4.3 | 25.5 Grok Build 0.1 |
| Knowledge & language | 33.0 Grok 4.3 | 31.2 Grok Build 0.1 |
| Human preference | 50.0 Grok 4.3 | 45.0 Grok Build 0.1 |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
Grok 4.3 leads on 5 of the 9 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Grok 4.3 | Grok Build 0.1 |
|---|---|---|
| LMArena WebDev (LMArena) | 1358 | 1166 |
| LiveBench Agentic Coding (LiveBench) | 18.5% | 45.8% |
| LiveBench Coding (LiveBench) | 69.9% | 65.4% |
| LiveBench Data Analysis (LiveBench) | 55.8% | 70.8% |
| LiveBench Instruction Following (LiveBench) | 62.8% | 65.2% |
| LiveBench Language (LiveBench) | 73.6% | 72.5% |
| LiveBench Mathematics (LiveBench) | 84.3% | 78.4% |
| LiveBench Reasoning (LiveBench) | 70.8% | 76.4% |
| WeirdML (Håvard Tveit Ihle) | 49.9% | 35.1% |
FAQ
Is Grok 4.3 better than Grok Build 0.1?
Grok 4.3 scores 22.2 on the Respan Index (#118), ahead of Grok Build 0.1 at 20.8 (#124). Grok 4.3 leads on 5 of the 9 benchmarks both report.
Which is cheaper, Grok 4.3 or Grok Build 0.1?
Grok 4.3 lists at $1.25 input and $2.5 output per 1M tokens; Grok Build 0.1 at $1 and $2. Grok Build 0.1 is 1.3x cheaper per token at list price.
Which has the larger context window?
Grok 4.3 accepts 1M tokens and Grok Build 0.1 256K tokens.