Grok 4.5
| Released | 2026-07-08 |
|---|---|
| Price per 1M | $2.00 in · $6.00 out |
| Overall score | 57.5 · rank 57 |
| Context window | 500,000 tokens |
| Provider | xAI |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 57.5 | 57 | 42 |
| Overall: Coding | 58.5 | 45 | 29 |
| Overall: Reasoning | 58.6 | 53 | 16 |
| Overall: Agentic work | 58.9 | 43 | 27 |
| Overall: Frontend | 55.8 | 56 | 13 |
| Coding | 58.9 | 36 | 9 |
| Agents | 58.7 | 42 | 9 |
| Reasoning | 59.8 | 47 | 9 |
| Math | 57.5 | 48 | 4 |
| Knowledge | 58.0 | 43 | 3 |
| Frontend | 55.9 | 49 | 2 |
| General | 54.0 | 75 | 4 |
| Multimodal | 45.3 | 91 | 2 |
| Value vs price | +6.4 | 57 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 59.0 ±3.3 | 8 |
| High | 56.9 ±0.7 | 34 |
| Low | 56.2 ±6.7 | 3 |
| Medium | 58.0 ±6.7 | 3 |
Evidence
Coding 58.9 ±1.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| DeepSWE | 53.8% | Epoch AI | 2026-11-11 |
| FrontierCode | 42.4% | Epoch AI | 2026-11-11 |
| SWE-rebench | 63.8% | SWE-rebench | 2026-07-01 |
| MirrorCode | 32.2% | Epoch AI | 2026-10-21 |
| IOI | 40.6% | Vals AI | 2026-10-29 |
| SWE-bench Verified (Vals run) | 86.6% | Vals AI | 2026-09-01 |
| SciCode | 55.0% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 87.4% | Vals AI | 2026-09-01 |
| ProgramBench | 0.0% | Vals AI | 2026-11-09 |
Agents 58.7 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SRE Bench | 0.8% | Vals AI | 2026-11-05 |
| Terminal-Bench 4 | 12.4% | Terminal-Bench | 2026-07-16 |
| APEX-Agents | 56.2% | Epoch AI | 2026-11-11 |
| Terminal-Bench 4.0 (Vals run) | 8.6% | Vals AI | 2026-11-09 |
| Terminal-Bench 2.1 (Vals run) | 67.8% | Vals AI | 2026-10-01 |
| tau2-bench Banking Knowledge | 47.9% | tau2-bench | 2026-07-24 |
| Tax Agent Bench | 24.9% | Vals AI | 2026-11-09 |
| SkillsBench | 66.0% | Vals AI | 2026-10-29 |
| Vending-Bench 2 | $3,887 | Epoch AI | 2026-11-11 |
| CyberBench v1.1 | 71.0% | Vals AI | 2026-11-05 |
Reasoning 59.8 ±1.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 52.6% | Epoch AI | 2026-11-11 |
| Extended NYT Connections | 79.9% | Lech Mazur | 2026-11-10 |
| ARC-AGI-2 (ARC Prize verified) | 52.6% | ARC Prize | 2026-11-11 |
| CritPt | 15.4% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 87.2% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 87.2% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 93.4% | Epoch AI | 2026-07-08 |
| GPQA Diamond (Vals run) | 92.9% | Vals AI | 2026-09-01 |
| ARC-AGI-3 | 0.3% | ARC Prize | 2026-11-11 |
| Kagi Reasoning Benchmark | 83.5% | Kagi | 2026-11-11 |
| Chess Puzzles | 35.0% | Epoch AI | 2026-10-13 |
| SimpleBench | 70.0% | SimpleBench | 2026-07-08 |
| SimpleBench | 70.0% | Epoch AI | 2026-11-11 |
Math 57.5 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 57.2% | Epoch AI | 2026-07-09 |
| FrontierMath Tier 4 | 24.4% | Epoch AI | 2026-07-09 |
| OTIS Mock AIME 2024-2025 | 97.8% | Epoch AI | 2026-07-08 |
| ProofBench v1.1 | 31.0% | Vals AI | 2026-11-09 |
| ProofBench | 31.0% | Epoch AI | 2026-11-11 |
Knowledge 58.0 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 48.3% | Epoch AI | 2026-08-27 |
| MMLU-Pro (Vals run) | 89.2% | Vals AI | 2026-09-01 |
| Legal Research Bench | 38.0% | Vals AI | 2026-11-09 |
Frontend 55.9 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 69.0% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,552 | LMArena | 2026-11-09 |
General 54.0 ±5.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LLM Debate Benchmark | 1,483 | Lech Mazur | 2026-10-26 |
| EQ-Bench Creative Writing v3 | 1,576 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,466 | LMArena | 2026-11-09 |
| Creative Story-Writing (Lech Mazur) | 2.0% | Lech Mazur | 2026-10-23 |
Multimodal 45.3 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 61.8% | Vals AI | 2026-09-01 |
| LMArena Vision | 1,280 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-1 | 85.7% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 79.2% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 85.7% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 79.2% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 | 52.6% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 33.1% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 52.6% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 33.1% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-3 | 0.3% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-3 | 0.3% | ARC Prize | A stronger configuration result was used |
Names matched to this model
grok-4-5