Up to four models
Grok 4.1 Fast vs Claude Sonnet 4.5
On the index (GPT-4 = 100), Grok 4.1 Fast scores 144 and Claude Sonnet 4.5 144. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Claude Sonnet 4.5
144129–160
WeightsClosed
ReleasedSep 2025
Price in / out$3.0 / $15
Context1M
Core tests taken6 of 9
Grok 4.1 Fast and Claude Sonnet 4.5 are too close to call (0 points apart, within the uncertainty).
Test by testthird-party results
Grok 4.1 FastClaude Sonnet 4.5
Every result as a table
| Test | Grok 4.1 Fast | Claude Sonnet 4.5 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Vals AI) | 84.3% | 81.6% |
| MMLU Pro | 84.2% | 87.4% |
| MMMU Pro | 72.7% | 79.3% |
| SimpleBench | 56.0% | 54.3% |
| Maths | ||
| MGSM | 89.5% | 94.3% |
| Coding | ||
| LiveCodeBench | 80.6% | 73.0% |
| SWE-bench | 41.4% | 70.0% |
| Vibe Code Bench v1.1 | 1.2% | 22.6% |
| Agents | ||
| DTBench | 87.7% | 83.2% |
| Professional work | ||
| CorpFin v2 | 66.0% | 62.0% |
| LegalBench | 82.5% | 84.1% |
| MedCode | 28.1% | 44.1% |
| MedScribe | 78.7% | 84.5% |
| MortgageTax | 42.6% | 64.0% |
| TaxEval v2 | 73.1% | 73.3% |
Task length · METR40 sec
Tests at least two of these models have taken. Bold rows are the core tests.