Grok 4.3 Beta
Grok 4.3 Beta.
xAI Released 17 Apr 2026
17
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
xAI Apr 2026
Grok 4.3 Beta
Closed weights
148.9
#68 of 271
Epoch Capabilities Index
- CritPt 8.00% #64 /160
- GDP.pdf 8.00% #38 /39
- GPQA Diamond 88.8% #50 /219
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SimpleQA Verified | 33.2% | #61 of 84 | Epoch AI |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GPQA Diamond | 88.8% | #50 of 219 | Epoch AI | |
| DTBench | 90.7% | #41 of 177 | Epoch AI | |
| OTIS Mock AIME 2024-2025 | 93.3% | #51 of 202 | Epoch AI | |
| CritPt | 8.00% | #64 of 160 | Epoch AI | |
| ForecastBench | 63.4 | #49 of 83 | Epoch AI | |
| FrontierMath Tiers 1-3 v2 | 42.8% | #60 of 89 | Epoch AI | |
| FrontierMath Tier 4 v2 | 14.6% | #56 of 71 | Epoch AI | |
| ProofBench | 11% | #67 of 83 | Epoch AI |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| WeirdML | 49.9% | #48 of 130 | Epoch AI | |
| ALE-Bench | 944 | #57 of 121 | Epoch AI | |
| WebDev Arena | 1,357 | #81 of 105 | Epoch AI |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Chess Puzzles | 18% | #66 of 83 | Epoch AI |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vending-Bench 2 | $35 | #60 of 65 | Epoch AI |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GDP.pdf | 8.00% | #38 of 39 | Epoch AI | |
| Blueprint-Bench 2 | 0% | #35 of 35 | Epoch AI |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LMCA | 38.3% | #57 of 139 | Epoch AI |
xAI's models over time
xAI's models in color, against every other model on the Epoch Capabilities Index, by release date.