xAIGrok
Grok 4.5
xAI · Grok. Released Jul 8, 2026.
Grok 4.5 is a model from xAI in the Grok family, released Jul 8, 2026. evals.report tracks 6 reported Grok 4.5 benchmark scores across ARC-AGI-1, ARC-AGI-2, FrontierCode, Terminal-Bench 2.1, SWE-bench Pro, SWE-Marathon — each shown with its benchmark, metric, source status, and date, and never combined into a single ranking.
6 results
Benchmark results 6
Compare this model| Benchmark | Category | Score | Metric | Status | Date | |
|---|---|---|---|---|---|---|
| ARC-AGI-1 | Reasoning | 85.67% | accuracy | Official | Jul 8, 2026 | Details |
| ARC-AGI-2 | Reasoning | 52.64% | accuracy | Official | Jul 8, 2026 | Details |
| FrontierCode | Coding | 42.4% | weighted score (Main) | Official | Jul 8, 2026 | Details |
| Terminal-Bench 2.1 | Agents | 83.3% | task success | Verified | Jul 8, 2026 | Details |
| SWE-bench Pro | Coding | 64.7% | % resolved | Verified | Jul 8, 2026 | Details |
| SWE-Marathon | Agents | 29.0% | resolution rate (pass@1) | Verified | Jul 8, 2026 | Details |