#12 Grok 4.5
high- Cost
- $0.015
- Time
- 29.7s
- Tokens
- 2,737 tok
X AI
Release: 2026-07-08
Tested on: 2026-07-17 00:48
x-ai/grok-4.5::high
~1.7T total (~170B active)MoEClosedEstimated
Summary
Grok 4.5 scores 8.9 on AI BENCHY and ranks #12. It has 10.0 reliability, a 83.3% pass rate, $2.904 total cost, and 76.50s average response time.
Model facts
Researched on 2026-08-12
- Parameters
- ~1.7T total (~170B active)
- Architecture
- MoE
- Availability
- Closed
- License
- -
Best estimate from public evidence; the vendor did not disclose every value. Low-confidence external estimate; xAI does not disclose the count.
8.9
Consistency
9.2
10.0
Total Output Tokens
253,195
Total Input Tokens
151,562
Input Price
$5.881 / 1M
Output Price
$5.881 / 1M
Flaky tests
2
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-08-14 02:59 Re-test | 9.0 | 10.0 | $2.252 ↑ | Compare | |
| 2026-07-17 00:48 Initial run | 8.9 | 10.0 | $2.904 ↑ | Current run |
Run comparison
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-07-17 00:48 · Initial run | 66/66 attempts | 8.9 | 9.2 | 10.0 | 17/22 | 2 | 253,195 | 151,562 | $2.904 | 76.50s |
| 2026-08-14 02:59 · Re-test | 66/66 attempts | 9.0 | 8.9 | 10.0 | 17/22 | 3 | 324,462 | 152,175 | $2.252 | 72.30s |
| Difference | — | 0.0 | +0.3 | 0.0 | 0 | -1 | -71267 | -613 | +$0.653 | +4205ms |
These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Grok 4.5highvsQwen3.8 MaxmediumGrok 4.5highvsGPT-5.3-CodexmediumGrok 4.5highvsGPT-5.5mediumGrok 4.5highvsSeed 2.1 TurbohighGrok 4.5highvsGemini 3.5 FlashmediumGrok 4.5highvsGemini 3.5 FlashlowGrok 4.5highvsQwen3.7 MaxmediumGrok 4.5highvsGemini 3.5 Flash LitehighGrok 4.5highvsSeed 2.1 TurbolowGrok 4.5highvsClaude Opus 4.8medium
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 10.0 | 10.0 | |
| Coding | 10.0 | 10.0 | |
| Combined | 10.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 3.6 | 7.2 | |
| General Intelligence | 4.7 | 1.6 | |
| Instructions following | 9.8 | 10.0 | |
| Puzzle Solving | 10.0 | 10.0 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |