#37 SpaceXAI: Grok 4.5
medium- Cost
- $0.044
- Time
- 59.4s
- Tokens
- 7,512 tok
X AI
Release: 2026-07-08
Tested on: 2026-08-14 03:04
x-ai/grok-4.5::medium
~1.7T total (~170B active)MoEClosedEstimated
Summary
Grok 4.5 scores 8.5 on AI BENCHY and ranks #37. It has 10.0 reliability, a 83.3% pass rate, $2.042 total cost, and 68.59s average response time.
What makes Grok 4.5 unique: It stands out most in Puzzle Solving, where it ranks #1, while Coding is its weakest area at #16.
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.
8.5
Consistency
8.9
10.0
$2.042
Total Output Tokens
299,460
Total Input Tokens
122,155
Input Price
$2.000 / 1M
Output Price
$6.000 / 1M
Flaky tests
3
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 03:04 Re-test | 8.5 | 10.0 | $2.042 | Current run | |
| 2026-07-16 23:09 New test added | 8.3 | 10.0 | $1.928 | Compare | |
| 2026-07-08 23:28 Re-test | 8.3 | 9.9 | $1.696 | Compare | |
| 2026-07-08 21:34 Initial run | 8.3 | 9.6 | $1.327 | Compare |
This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.
Run comparison
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-08-14 03:04 · Current run | 66/66 attempts | 8.5 | 8.9 | 10.0 | 17/22 | 3 | 299,460 | 122,155 | $2.042 | 68.59s |
| 2026-07-16 23:09 · New test added | 66/66 attempts | 8.3 | 8.9 | 10.0 | 16/22 | 3 | 280,567 | 122,146 | $1.928 | 61.71s |
| Difference | — | +0.1 | 0.0 | 0.0 | +1 | 0 | +18893 | +9 | +$0.114 | +6879ms |
These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.
Price History
Historical pricing data for this model from OpenRouter.
| Date | Input Price | Output Price |
|---|---|---|
| 2026-08-14 12:51 | $2.000 / 1M | $6.000 / 1M |
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 4.5mediumvsGPT-5.4mediumGrok 4.5mediumvsMuse Spark 1.2lowGrok 4.5mediumvsQwen3.8 MaxlowGrok 4.5mediumvsGrok 4.6mediumGrok 4.5mediumvsQwen3.6 Max PreviewmediumGrok 4.5mediumvsGrok 4.5lowGrok 4.5mediumvsClaude Fable 5mediumGrok 4.5mediumvsGPT-5.2mediumGrok 4.5mediumvsMuse Spark 1.1mediumGrok 4.5mediumvsQwen3.8 27Bhigh
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 10.0 | 10.0 | |
| Coding | 7.6 | 7.2 | |
| Combined | 10.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 5.3 | 7.2 | |
| General Intelligence | 6.5 | 3.4 | |
| Instructions following | 9.8 | 10.0 | |
| Puzzle Solving | 10.0 | 10.0 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |