← All benchmarks
Grok 4.20 0309 v2 (Reasoning)
SpaceXAI · Released 2026-04-07 · Independent benchmark scores from Artificial Analysis
Intelligence Index
37.0
Output speed
0.0
tokens/sec
Blended price
$3.00
per 1M tokens
Time to first token
0.00s
Model metadata
| Model ID | c72cb85a-18a4-4235-b455-77dff2f16c50 |
|---|---|
| Slug | grok-4-20 |
| Release date | 2026-04-07 |
| Provider | SpaceXAI |
| Provider slug | xai |
| Output speed | 0.0 tok/s |
| Time to first token | 0.00s |
| Time to first answer | 0.00s |
| Blended price ($/1M) | $3.00 |
| Input price ($/1M) | $2.00 |
| Output price ($/1M) | $6.00 |
All evaluation scores (17)
| aime | — |
|---|---|
| aime 25 | — |
| artificial analysis coding index | — |
| artificial analysis intelligence index | 37.00 |
| artificial analysis math index | — |
| gpqa | 91.1% |
| hle | 32.2% |
| ifbench | 81.2% |
| lcr | 58.0% |
| livecodebench | — |
| math 500 | — |
| mmlu pro | — |
| scicode | 45.6% |
| tau banking | — |
| tau2 | 93.0% |
| terminalbench hard | 37.9% |
| terminalbench v2 1 | — |
Source: artificialanalysis.ai/models/grok-4-20
Benchmark data from Artificial Analysis.