# Claude Opus 4.7 vs Grok 4.20 (Non-Reasoning)

> Claude Opus 4.7 is the stronger model overall, scoring 58.3 to 48.6 on the Noometry Index. Grok 4.20 (Non-Reasoning) costs 6.4× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-opus-4-7-vs-grok-4-20
- Last updated: 2026-10-12
- Shared benchmarks: 44

## Summary

- They share 44 benchmarks with published results for both. Claude Opus 4.7 scores higher in 10 categories and Grok 4.20 (Non-Reasoning) in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4.7 leads 66.7 to 48.2.
- The biggest single-benchmark swing is NYT Connections (extended): 39% for Claude Opus 4.7 and 85.4% for Grok 4.20 (Non-Reasoning).
- Grok 4.20 (Non-Reasoning) is cheaper at $1.25 / $2.50 per million input/output tokens, against $5 / $25 for Claude Opus 4.7.

## Snapshot

| | Claude Opus 4.7 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 58.3 | 48.6 |
| Rank | 19 | 54 |
| Context | 1M | 1M |
| Input $/M | $5 | $1.25 |
| Output $/M | $25 | $2.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 4.7: 59.6 (#13)
- Grok 4.20 (Non-Reasoning): 42.1 (#112)

| Benchmark | Claude Opus 4.7 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena WebDev | 1558 | 1375 |
| WeirdML | 76.4% | 52.3% |
| LMArena Coding | 1518 | 1459 |
| ALE-Bench | 1,323 | 1,150 |
| SWE-bench Verified | 83.5% | — |
| FrontierCode | 38.5% | — |
| SciCode | 54.5% | — |
| GSO | 44.1% | — |
| MirrorCode | 31.1% | — |

## Agentic & Tool Use

- Claude Opus 4.7: 47.9 (#10)
- Grok 4.20 (Non-Reasoning): 34.4 (#46)

| Benchmark | Claude Opus 4.7 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | 80.2% | 57.3% |
| τ²-bench Banking | 40.2% | 18% |
| LMArena Search | 1233 | 1189 |
| Vending-Bench 2 | 10,937 | 4,663 |
| APEX-Agents | 49.2% | — |
| OSWorld 2.0 | 18.2% | — |
| PostTrainBench | 28.6% | — |
| ExploitBench | 26.5% | — |
| GBAEval | 43.8% | — |
| GDP.pdf | 21% | — |

## Reasoning

- Claude Opus 4.7: 53.8 (#29)
- Grok 4.20 (Non-Reasoning): 52.3 (#32)

| Benchmark | Claude Opus 4.7 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| ARC-AGI-2 | 75.8% | 65.1% |
| Kagi LLM Benchmark | 80.7% | 75% |
| NYT Connections (extended) | 39% | 85.4% |
| ARC-AGI-1 | 93.5% | 89.5% |
| Chess Puzzles | 30% | 24% |
| Thematic Generalization | 72.8% | 63.8% |
| LMArena Hard Prompts | 1506 | 1451 |
| DTBench | 94.7% | 90.1% |
| LMCA | 52.2% | 38.7% |
| Epoch Capabilities Index | 156.25 | 151.98 |
| ForecastBench | 60.3 | 61.4 |
| SimpleBench | 61.7% | — |
| CritPt | 12% | — |
| EBR-Bench | 19% | — |
| Mystery Game Puzzles | 28% | — |

## Math

- Claude Opus 4.7: 66.7 (#26)
- Grok 4.20 (Non-Reasoning): 48.2 (#65)

| Benchmark | Claude Opus 4.7 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| FrontierMath (Tiers 1-3) | 70.2% | 44.9% |
| FrontierMath Tier 4 | 31.7% | 17.1% |
| OTIS Mock AIME 2024-2025 | 97.8% | 92.2% |
| ProofBench | 54% | 14% |
| LMArena Math | 1499 | 1455 |
| MathArena Final-Answer Competitions | 73.6% | — |
| FrontierMath (Feb 2025 set) | 43.8% | — |
| FrontierMath Tier 4 (v1) | 22.9% | — |

## Knowledge

- Claude Opus 4.7: 62.6 (#23)
- Grok 4.20 (Non-Reasoning): 52.8 (#60)

| Benchmark | Claude Opus 4.7 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 90.2% | 89.3% |
| SimpleQA Verified | 51.7% | 30.2% |
| LMArena Expert | 1521 | 1439 |
| Humanity's Last Exam | 36.2% | — |
| Vectara Hallucination Rate | 12% | — |

## Multimodal

- Claude Opus 4.7: 41.2 (#38)
- Grok 4.20 (Non-Reasoning): 33.3 (#98)

| Benchmark | Claude Opus 4.7 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | 1316 | 1263 |
| Blueprint-Bench 2 | 24.5% | 0% |
| LMArena Document | 1495 | 1416 |
| Furniture Assembly | 33.3% | — |

## Multilingual

- Claude Opus 4.7: 57.3 (#10)
- Grok 4.20 (Non-Reasoning): 54.5 (#40)

| Benchmark | Claude Opus 4.7 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1480 | 1441 |
| LMArena Chinese | 1531 | 1481 |
| LMArena French | 1503 | 1476 |
| LMArena German | 1495 | 1465 |
| LMArena Japanese | 1472 | 1449 |
| LMArena Korean | 1464 | 1417 |
| LMArena Russian | 1494 | 1458 |
| LMArena Spanish | 1495 | 1443 |

## Instruction Following

- Claude Opus 4.7: 78.4 (#10)
- Grok 4.20 (Non-Reasoning): 74.8 (#83)

| Benchmark | Claude Opus 4.7 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1498 | 1420 |

## Long Context

- Claude Opus 4.7: 46.2 (#25)
- Grok 4.20 (Non-Reasoning): 45.5 (#34)

| Benchmark | Claude Opus 4.7 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1505 | 1437 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |

## Writing & Preference

- Claude Opus 4.7: 75.1 (#8)
- Grok 4.20 (Non-Reasoning): 65.7 (#44)

| Benchmark | Claude Opus 4.7 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1490 | 1451 |
| LMArena Creative Writing | 1486 | 1438 |
| EQ-Bench Creative Writing | 1914 | 1574 |
| LMArena Multi-Turn | 1505 | 1456 |
| EQ-Bench 4 | 1311 | — |

## FAQ

### Is Claude Opus 4.7 better than Grok 4.20 (Non-Reasoning)?

Claude Opus 4.7 is the stronger model overall, scoring 58.3 to 48.6 on the Noometry Index. Grok 4.20 (Non-Reasoning) costs 6.4× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

### Which is cheaper, Claude Opus 4.7 or Grok 4.20 (Non-Reasoning)?

Grok 4.20 (Non-Reasoning) is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; Claude Opus 4.7 lists at $5 and $25.

### Is Claude Opus 4.7 or Grok 4.20 (Non-Reasoning) better for coding?

Claude Opus 4.7 scores higher on coding benchmarks: 59.6 versus 42.1 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1M tokens.

### How many benchmarks do Claude Opus 4.7 and Grok 4.20 (Non-Reasoning) share?

44 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.