Grok 4.7
| Released | 2026-09-21 |
|---|---|
| Price per 1M | $2.00 in · $6.00 out |
| Overall score | 60.1 · rank 28 |
| Context window | 500,000 tokens |
| Provider | xAI |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 60.1 | 28 | 52 |
| Overall: Coding | 60.8 | 22 | 40 |
| Overall: Reasoning | 59.0 | 45 | 18 |
| Overall: Agentic work | 60.8 | 23 | 37 |
| Overall: Frontend | 59.8 | 24 | 15 |
| Coding | 61.1 | 19 | 11 |
| Agents | 60.8 | 22 | 14 |
| Reasoning | 60.6 | 39 | 12 |
| Math | 56.8 | 55 | 4 |
| Knowledge | 59.3 | 32 | 2 |
| Frontend | 59.8 | 23 | 3 |
| General | 62.0 | 19 | 5 |
| Multimodal | 55.3 | 46 | 1 |
| Value vs price | +9.1 | 35 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 60.9 ±2.0 | 12 |
| High | 61.1 ±3.5 | 10 |
| Low | 56.7 ±4.0 | 6 |
| Medium | 60.5 ±4.2 | 4 |
| Extra High | 59.4 ±0.7 | 37 |
Evidence
Coding 61.1 ±0.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| CursorBench | 46.3% | Epoch AI | 2026-11-11 |
| FrontierSWE | 29.5% | Epoch AI | 2026-11-11 |
| FrontierCode | 47.6% | Epoch AI | 2026-11-11 |
| Code Migration v1.1 | 53.2% | Vals AI | 2026-11-09 |
| LiveBench 2.0 Coding | 73.1% | LiveBench | 2026-11-06 |
| WeirdML v3 | 8.5% | Epoch AI | 2026-11-11 |
| MirrorCode | 54.4% | Epoch AI | 2026-10-29 |
| IOI | 57.7% | Vals AI | 2026-10-29 |
| SWE-bench Multimodal | 42.9% | Vals AI | 2026-11-09 |
| SciCode | 57.8% | Epoch AI | 2026-11-11 |
| ProgramBench | 0.5% | Vals AI | 2026-11-09 |
Agents 60.8 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4 | 38.8% | Terminal-Bench | 2026-09-21 |
| SRE Bench | 3.8% | Vals AI | 2026-11-05 |
| Terminal-Bench-Science | 10.0% | Vals AI | 2026-11-09 |
| Terminal-Bench 4.0 (Vals run) | 28.8% | Vals AI | 2026-11-09 |
| APEX-Agents | 54.6% | Epoch AI | 2026-11-11 |
| LiveBench 2.0 Agentic | 45.3% | LiveBench | 2026-11-06 |
| LiveBench 2.0 Browser Use | 49.3% | LiveBench | 2026-11-06 |
| Terminal-Bench 2.1 (Vals run) | 73.4% | Vals AI | 2026-10-01 |
| EMB v1.1 (Excel financial modeling) | 71.5% | Vals AI | 2026-11-09 |
| LiveBench 2.0 Research | 89.5% | LiveBench | 2026-11-06 |
| Tax Agent Bench | 35.8% | Vals AI | 2026-11-09 |
| Finance Agent v2.1 | 60.6% | Vals AI | 2026-11-09 |
| Vending-Bench 2 | $10,537 | Epoch AI | 2026-11-11 |
| HLAB-Vals 1.1 (legal agent) | 18.3% | Vals AI | 2026-11-09 |
| CyberBench v1.1 | 69.5% | Vals AI | 2026-11-05 |
Reasoning 60.6 ±1.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 61.4% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 61.4% | ARC Prize | 2026-11-11 |
| Extended NYT Connections | 76.8% | Lech Mazur | 2026-11-10 |
| MysteryMechanism | 25.2% | Vals AI | 2026-11-09 |
| GPQA Diamond | 92.7% | Epoch AI | 2026-09-22 |
| CritPt | 18.0% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 90.2% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 90.2% | Epoch AI | 2026-11-11 |
| BioMysteryBench | 69.3% | Vals AI | 2026-11-09 |
| ARC-AGI-3 | 10.1% | ARC Prize | 2026-11-11 |
| Chess Puzzles | 41.0% | Epoch AI | 2026-10-13 |
| LiveBench 2.0 Reasoning | 82.7% | LiveBench | 2026-11-06 |
| Mystery Game Puzzles | 29.0% | Epoch AI | 2026-09-22 |
| LiveBench 2.0 Data Analysis | 76.9% | LiveBench | 2026-11-06 |
Math 56.8 ±1.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 53.0% | Epoch AI | 2026-09-22 |
| FrontierMath Tier 4 | 17.1% | Epoch AI | 2026-09-22 |
| OTIS Mock AIME 2024-2025 | 98.1% | Epoch AI | 2026-09-22 |
| ProofBench v1.1 | 26.0% | Vals AI | 2026-11-09 |
| ProofBench | 26.0% | Epoch AI | 2026-11-11 |
Knowledge 59.3 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 56.0% | Epoch AI | 2026-09-22 |
| Legal Research Bench | 47.1% | Vals AI | 2026-11-09 |
Frontend 59.8 ±1.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LiveBench 2.0 Design | 75.0% | LiveBench | 2026-11-06 |
| Vibe Code Bench v1.1 | 86.2% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,639 | LMArena | 2026-11-09 |
General 62.0 ±4.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LLM Debate Benchmark | 1,614 | Lech Mazur | 2026-10-26 |
| EQ-Bench Creative Writing v3 | 2,012 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,442 | LMArena | 2026-11-09 |
| Creative Story-Writing (Lech Mazur) | 55.0% | Lech Mazur | 2026-10-23 |
| EQ-Bench Longform Creative Writing | 83.0% | EQ-Bench | 2026-11-11 |
Multimodal 55.3 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Vision | 1,249 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-1 | 89.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 90.0% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 63.3% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 89.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 90.0% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 63.3% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 | 58.3% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 58.8% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 16.7% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 58.3% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 58.8% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 16.7% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-3 | 1.8% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-3 | 7.0% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-3 | 1.7% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-3 | 1.7% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-3 | 8.4% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-3 | 0.3% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-3 | 0.8% | ARC Prize | A stronger configuration result was used |
| CritPt | 17.7% | Epoch AI | A stronger configuration result was used |
| CritPt | 13.4% | Epoch AI | A stronger configuration result was used |
| CursorBench | 43.9% | Epoch AI | A stronger configuration result was used |
| CursorBench | 41.6% | Epoch AI | A stronger configuration result was used |
| CursorBench | 33.1% | Epoch AI | A stronger configuration result was used |
| SciCode | 57.4% | Epoch AI | A stronger configuration result was used |
| SciCode | 54.9% | Epoch AI | A stronger configuration result was used |
Names matched to this model
grok-4-7