Grok 4.5
Grok 4.5 is an API-only (closed weights) language model from xAI, released July 8, 2026. Its makers disclosed about 1.5T parameters. The context window is 488K tokens. On the Epoch Capabilities Index it scores 155.0, rank 46 of 256 rated models. API price: $2 input / $6 output per million tokens.
Check it against your own PC →
Lab
xAI
Released
July 8, 2026
Weights
API-only (closed weights)
Parameters
1.5T disclosed
Context
488K
Price / M tokens
$2 / $6 in / out
Epoch ECI
155.0 #46
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Reasoning | 24.0 | Chess Puzzles, SimpleBench |
| Math | 45.8 | ProofBench, OTIS Mock AIME 2024-2025, FrontierMath-Tiers-1-3-v2-Private, FrontierMath-Tier-4-v2-Private |
| Coding | 51.9 | MirrorCode, DeepSWE |
| Knowledge | 76.7 | GPQA diamond, SimpleQA Verified |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| OTIS Mock AIME | 97.8% |
| GPQA Diamond | 95.0% |
| SimpleBench | 64.0% |
| FrontierMath (Tiers 1–3) | 60.2% |
| DeepSWE | 53.8% |
| SimpleQA Verified | 48.3% |
| MirrorCode | 32.2% |
| Chess Puzzles | 31.6% |
| ProofBench | 31.0% |
| FrontierMath-Tier-4-v2-Private | 24.4% |
| Furniture Assembly | 0.0% |
Links
Announcement · Epoch AI benchmarks
Models with a similar score
Gemini 3.8 Flash · Kimi K3 · Gemini 3.7 Flash · Muse Spark 1.3 · GPT-5.4 · Grok 4.6 · Qwen 3.8 Max · Claude Opus 4.7
More from xAI
Grok 4.7 · Grok 4.6 · Grok 4.3 Beta · Grok Build 0.1 · Grok 4.20 Multi-Agent · Grok 4.20 · Grok 4.1 Fast · Grok 4.1