Grok 4.6
| Released | 2026-08-12 |
|---|---|
| Price per 1M | $2.00 in · $6.00 out |
| Overall score | 59.8 · rank 31 |
| Context window | 500,000 tokens |
| Provider | xAI |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 59.8 | 31 | 49 |
| Overall: Coding | 60.5 | 23 | 38 |
| Overall: Reasoning | 60.3 | 31 | 20 |
| Overall: Agentic work | 60.7 | 25 | 35 |
| Overall: Frontend | 59.2 | 30 | 15 |
| Coding | 60.9 | 23 | 11 |
| Agents | 60.4 | 25 | 11 |
| Reasoning | 61.6 | 33 | 13 |
| Math | 59.2 | 35 | 4 |
| Knowledge | 59.4 | 29 | 3 |
| Frontend | 58.6 | 34 | 3 |
| General | 56.2 | 56 | 3 |
| Multimodal | 57.3 | 32 | 1 |
| Value vs price | +8.8 | 39 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 62.1 ±2.4 | 11 |
| High | 59.6 ±0.8 | 33 |
| Low | 56.1 ±4.3 | 6 |
| Medium | 60.1 ±4.3 | 6 |
| Extra High | 59.6 ±2.7 | 17 |
Evidence
Coding 60.9 ±1.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| CursorBench | 41.4% | Epoch AI | 2026-11-11 |
| FrontierSWE | 25.3% | Epoch AI | 2026-11-11 |
| DeepSWE | 67.5% | Epoch AI | 2026-11-11 |
| FrontierCode | 48.0% | Epoch AI | 2026-11-11 |
| LiveBench 2.0 Coding | 76.7% | LiveBench | 2026-11-06 |
| MirrorCode | 41.1% | Epoch AI | 2026-10-21 |
| IOI | 47.6% | Vals AI | 2026-10-29 |
| SWE-bench Verified (Vals run) | 95.6% | Vals AI | 2026-09-01 |
| SciCode | 56.5% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 88.2% | Vals AI | 2026-09-01 |
| ProgramBench | 1.0% | Vals AI | 2026-11-09 |
Agents 60.4 ±1.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4 | 19.7% | Terminal-Bench | 2026-08-12 |
| Terminal-Bench-Science | 11.4% | Vals AI | 2026-11-09 |
| APEX-Agents | 65.3% | Epoch AI | 2026-11-11 |
| Terminal-Bench 4.0 (Vals run) | 17.2% | Vals AI | 2026-11-09 |
| LiveBench 2.0 Agentic | 18.7% | LiveBench | 2026-11-06 |
| LiveBench 2.0 Browser Use | 49.4% | LiveBench | 2026-11-06 |
| Terminal-Bench 2.1 (Vals run) | 78.3% | Vals AI | 2026-10-01 |
| LiveBench 2.0 Research | 88.8% | LiveBench | 2026-11-06 |
| Tax Agent Bench | 33.7% | Vals AI | 2026-11-09 |
| SkillsBench | 55.8% | Vals AI | 2026-10-29 |
| Vending-Bench 2 | $9,047 | Epoch AI | 2026-11-11 |
| CyberBench v1.1 | 67.7% | Vals AI | 2026-11-05 |
Reasoning 61.6 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 67.1% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 67.1% | ARC Prize | 2026-11-11 |
| Extended NYT Connections | 80.0% | Lech Mazur | 2026-11-10 |
| MysteryMechanism | 30.6% | Vals AI | 2026-11-09 |
| CritPt | 19.7% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 87.5% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 87.5% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 94.0% | Epoch AI | 2026-08-12 |
| GPQA Diamond (Vals run) | 94.7% | Vals AI | 2026-09-01 |
| BioMysteryBench | 72.2% | Vals AI | 2026-11-09 |
| ARC-AGI-3 | 2.1% | ARC Prize | 2026-11-11 |
| Chess Puzzles | 33.0% | Epoch AI | 2026-10-13 |
| SimpleBench | 75.9% | SimpleBench | 2026-08-13 |
| SimpleBench | 75.9% | Epoch AI | 2026-11-11 |
| LiveBench 2.0 Reasoning | 91.2% | LiveBench | 2026-11-06 |
| Mystery Game Puzzles | 34.0% | Epoch AI | 2026-08-14 |
| LiveBench 2.0 Data Analysis | 75.3% | LiveBench | 2026-11-06 |
Math 59.2 ±1.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 66.0% | Epoch AI | 2026-08-14 |
| FrontierMath Tier 4 | 31.7% | Epoch AI | 2026-08-14 |
| OTIS Mock AIME 2024-2025 | 99.2% | Epoch AI | 2026-08-14 |
| ProofBench v1.1 | 51.0% | Vals AI | 2026-11-09 |
| ProofBench | 51.0% | Epoch AI | 2026-11-11 |
Knowledge 59.4 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 49.3% | Epoch AI | 2026-08-27 |
| MMLU-Pro (Vals run) | 89.4% | Vals AI | 2026-09-01 |
| Legal Research Bench | 48.1% | Vals AI | 2026-11-09 |
Frontend 58.6 ±1.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LiveBench 2.0 Design | 76.3% | LiveBench | 2026-11-06 |
| Vibe Code Bench v1.1 | 76.2% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,618 | LMArena | 2026-11-09 |
General 56.2 ±5.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,456 | LMArena | 2026-11-09 |
| LLM Debate Benchmark | 1,598 | Lech Mazur | 2026-10-26 |
| Creative Story-Writing (Lech Mazur) | 12.0% | Lech Mazur | 2026-10-23 |
Multimodal 57.3 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Vision | 1,263 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-1 | 87.0% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 87.0% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 74.8% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 87.0% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 87.0% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 74.8% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 | 65.1% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 61.3% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 27.6% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 65.1% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 61.3% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 27.6% | ARC Prize | A stronger configuration result was used |
| Chess Puzzles | 33.0% | Epoch AI | A stronger configuration result was used |
| CritPt | 17.1% | Epoch AI | A stronger configuration result was used |
| CritPt | 17.7% | Epoch AI | A stronger configuration result was used |
| CritPt | 5.7% | Epoch AI | A stronger configuration result was used |
| CursorBench | 40.4% | Epoch AI | A stronger configuration result was used |
| CursorBench | 36.1% | Epoch AI | A stronger configuration result was used |
| CursorBench | 33.4% | Epoch AI | A stronger configuration result was used |
| DeepSWE | 66.7% | Epoch AI | A stronger configuration result was used |
| DeepSWE | 65.2% | Epoch AI | A stronger configuration result was used |
| DeepSWE | 41.7% | Epoch AI | A stronger configuration result was used |
| Extended NYT Connections | 79.0% | Lech Mazur | A stronger configuration result was used |
| GPQA Diamond | 93.2% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 97.8% | Epoch AI | A stronger configuration result was used |
| SciCode | 53.0% | Epoch AI | A stronger configuration result was used |
| SciCode | 55.9% | Epoch AI | A stronger configuration result was used |
| SciCode | 49.4% | Epoch AI | A stronger configuration result was used |
| SimpleQA Verified | 48.9% | Epoch AI | A stronger configuration result was used |
Names matched to this model
grok-4-6