#17 SpaceXAI: Grok 4.6
high- Cost
- $0.107
- Time
- 265.1s
- Tokens
- 18,001 tok
X AI
Release: 2026-08-12
Tested on: 2026-08-14 04:41
x-ai/grok-4.6::high
~1.7T total (~170B active)MoEClosedEstimated
Summary
Grok 4.6 scores 9.3 on AI BENCHY and ranks #17. It has 10.0 reliability, a 86.4% pass rate, $1.908 total cost, and 84.15s average response time.
What makes Grok 4.6 unique: It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.
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. xAI exposes the exact API checkpoint but does not disclose its architecture or parameter counts; estimate follows the Grok 4 family.
9.3
Consistency
10.0
10.0
$1.908
Total Output Tokens
282,217
Total Input Tokens
107,275
Input Price
$2.000 / 1M
Output Price
$6.000 / 1M
Flaky tests
0
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 04:41 Re-test | 9.3 | 10.0 | $1.908 | Current run | |
| 2026-08-12 23:02 Initial run | 9.2 | 10.0 | $1.809 | 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 04:41 · Current run | 66/66 attempts | 9.3 | 10.0 | 10.0 | 19/22 | 0 | 282,217 | 107,275 | $1.908 | 84.15s |
| 2026-08-12 23:02 · Initial run | 66/66 attempts | 9.2 | 9.6 | 10.0 | 18/22 | 1 | 265,604 | 107,266 | $1.809 | 79.38s |
| Difference | — | +0.1 | +0.4 | 0.0 | +1 | -1 | +16613 | +9 | +$0.100 | +4772ms |
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 4.6highvsGPT-5.5lowGrok 4.6highvsGemini 3.1 Pro PreviewmediumGrok 4.6highvsGPT-5.6 SolhighGrok 4.6highvsGemini 3.7 FlashlowGrok 4.6highvsGPT-6 AstramediumGrok 4.6highvsClaude Opus 5highGrok 4.6highvsGPT-5.6 SolmediumGrok 4.6highvsClaude Opus 5mediumGrok 4.6highvsGemini 3.7 FlashmediumGrok 4.6highvsGemini 3.8 Flashmedium
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 | 5.3 | 10.0 | |
| General Intelligence | 10.0 | 10.0 | |
| Instructions following | 9.8 | 10.0 | |
| Puzzle Solving | 10.0 | 10.0 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |