- Score
- 9.4 (+0.82 points)
- Total Cost (Current Price)
- $0.183 · 93.1% cheaper
- Response Time (avg)
- 6.24s · 92.9% faster
X AI
Release: 2026-08-12
Tested on: 2026-10-01 04:17
x-ai/grok-4.6::high
~1.7T total (~170B active)MoEClosedEstimated
Summary
Grok 4.6 scores 8.5 on AI BENCHY and ranks #98. It has 10.0 reliability, a 82.6% pass rate, $2.629 total cost, and 87.48s average response time.
What makes Grok 4.6 unique: It stands out most in Domain specific, where it ranks #3, while Agentic is its weakest area at #15.
Recommended alternatives
We recommend choosing one of these models instead:
- Score
- 8.6 (+0.04 points)
- Total Cost (Current Price)
- $0.061 · 97.7% cheaper
- Response Time (avg)
- 7.51s · 91.4% faster
- Score
- 9.0 (+0.41 points)
- Total Cost (Current Price)
- $0.089 · 96.6% cheaper
- Response Time (avg)
- 54.04s · 38.2% faster
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.
8.5
Consistency
10.0
10.0
$2.629
Total Output Tokens
312,614
Total Input Tokens
376,233
Input Price
$2.000 / 1M
Output Price
$6.000 / 1M
Cache Read Price
$0.500 / 1M
Cache Write Price
N/A
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
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.
#98 SpaceXAI: Grok 4.6
high- Cost
- $0.107
- Time
- 265.1s
- Tokens
- 18,001 tok
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-10-01 04:17 Re-test | 8.5 | 10.0 | $2.629 | 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.
Price History
Historical pricing data for this model from OpenRouter.
| Date | Input Price | Output Price | Cache Read Price | Cache Write Price |
|---|---|---|---|---|
| 2026-08-14 12:51 | $2.000 / 1M | $6.000 / 1M | N/A | N/A |
| 2026-10-01 18:33 | $2.000 / 1M | $6.000 / 1M | $0.500 / 1M | N/A |
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 4.6highvsMuse EmbermediumGrok 4.6highvsMuse Spark 1.3lowGrok 4.6highvsParticle-1mediumGrok 4.6highvsClaude Sonnet 5mediumGrok 4.6highvsQwen3.8 Max (0902)lowGrok 4.6highvsQwen3.7 MaxmediumGrok 4.6highvsClaude Haiku 5.5lowGrok 4.6highvsClaude Haiku 5.5maxGrok 4.6highvsClaude Sonnet 5.5highGrok 4.6highvsNemotron 3.5 Super VLhighFree Available
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 5.0 | 10.0 | |
| 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 |