X-Ai/Grok-4-Fast-Reasoning
| Released | 2025-12-18 |
|---|---|
| Price per 1M | $0.20 in · $0.50 out |
| Overall score | 47.0 · rank 136 |
| Context window | 2,000,000 tokens |
| Provider | xAI |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 47.0 | 136 | 10 |
| Overall: Coding | 45.2 | 150 | 7 |
| Overall: Reasoning | 49.1 | 121 | 4 |
| Overall: Agentic work | 50.0 | 113 | 5 |
| Overall: Frontend | 35.4 | 201 | 5 |
| Coding | 48.9 | 122 | 2 |
| Reasoning | 51.9 | 101 | 3 |
| Knowledge | 42.9 | 127 | 1 |
| Frontend | 26.8 | 135 | 2 |
| General | 49.2 | 115 | 1 |
| Multimodal | 46.3 | 88 | 1 |
| Value vs price | +3.0 | 95 |
Evidence
Coding 48.9 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SWE-bench Verified (Vals run) | 45.4% | Vals AI | 2026-09-01 |
| LiveCodeBench (Vals run) | 79.0% | Vals AI | 2026-09-01 |
Reasoning 51.9 ±2.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-1 (ARC Prize verified) | 48.5% | ARC Prize | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 5.3% | ARC Prize | 2026-11-11 |
| GPQA Diamond (Vals run) | 85.4% | Vals AI | 2026-09-01 |
Knowledge 42.9 ±4.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMLU-Pro (Vals run) | 79.7% | Vals AI | 2026-09-01 |
Frontend 26.8 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 0.0% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,162 | LMArena | 2026-11-10 |
General 49.2 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,405 | LMArena | 2026-11-09 |
Multimodal 46.3 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 72.8% | Vals AI | 2026-09-01 |
Names matched to this model
grok-4-fast-reasoning