Model comparison
Claude Opus 4.7 vs Grok 4.20 Multi-Agent
Claude Opus 4.7 is the stronger model overall, scoring 58.4 to 45.5 on the Noometry Index. Grok 4.20 Multi-Agent 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.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. Claude Opus 4.7 scores higher in 9 categories and Grok 4.20 Multi-Agent in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4.7 leads 66.5 to 36.6.
- The biggest single-benchmark swing is NYT Connections (extended): 39% for Claude Opus 4.7 and 89.6% for Grok 4.20 Multi-Agent.
- Grok 4.20 Multi-Agent is cheaper at $1.25 / $2.50 per million input/output tokens, against $5 / $25 for Claude Opus 4.7.
Side by side
| Claude Opus 4.7 | Grok 4.20 Multi-Agent | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 58.4 | 45.5 |
| Released | 2026-04-14 | 2026-03-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1M |
| Max output | 128K | 30K |
| Input $ / M tokens | $5 | $1.25 |
| Output $ / M tokens | $25 | $2.50 |
| Results tracked | 66 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.7 leads
Claude Opus 4.7: 59.9 (#10), Grok 4.20 Multi-Agent: 42.4 (#91)
| Benchmark | Claude Opus 4.7 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Coding | 1519 | 1458 |
| SWE-bench Verified | 83.5% | — |
| FrontierCode | 38.5% | — |
| LMArena WebDev | 1557 | — |
| SciCode | 54.5% | — |
| GSO | 44.1% | — |
| WeirdML | 76.4% | — |
| MirrorCode | 31.1% | — |
| ALE-Bench | 1,323 | — |
Agentic & Tool Use Not comparable
Claude Opus 4.7: 47.9 (#8), Grok 4.20 Multi-Agent: —
| Benchmark | Claude Opus 4.7 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Search | 1233 | 1204 |
| Terminal-Bench | 80.2% | — |
| APEX-Agents | 49.2% | — |
| OSWorld 2.0 | 18.2% | — |
| τ²-bench Banking | 40.2% | — |
| PostTrainBench | 28.6% | — |
| ExploitBench | 26.5% | — |
| GBAEval | 43.8% | — |
| GDP.pdf | 21% | — |
| Vending-Bench 2 | 10,937 | — |
Reasoning Claude Opus 4.7 leads
Claude Opus 4.7: 53.7 (#24), Grok 4.20 Multi-Agent: 42.4 (#44)
| Benchmark | Claude Opus 4.7 | Grok 4.20 Multi-Agent |
|---|---|---|
| NYT Connections (extended) | 39% | 89.6% |
| LMArena Hard Prompts | 1507 | 1448 |
| ARC-AGI-2 | 75.8% | — |
| SimpleBench | 61.7% | — |
| Kagi LLM Benchmark | 80.7% | — |
| ARC-AGI-1 | 93.5% | — |
| CritPt | 12% | — |
| Chess Puzzles | 30% | — |
| Thematic Generalization | 72.8% | — |
| EBR-Bench | 19% | — |
| Mystery Game Puzzles | 28% | — |
| DTBench | 94.7% | — |
| LMCA | 52.2% | — |
| Epoch Capabilities Index | 156.39 | — |
| ForecastBench | 60.3 | — |
Math Claude Opus 4.7 leads
Claude Opus 4.7: 66.5 (#20), Grok 4.20 Multi-Agent: 36.6 (#106)
| Benchmark | Claude Opus 4.7 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Math | 1499 | 1441 |
| FrontierMath (Tiers 1-3) | 70.2% | — |
| FrontierMath Tier 4 | 31.7% | — |
| MathArena Final-Answer Competitions | 73.6% | — |
| OTIS Mock AIME 2024-2025 | 97.8% | — |
| ProofBench | 54% | — |
| FrontierMath (Feb 2025 set) | 43.8% | — |
| FrontierMath Tier 4 (v1) | 22.9% | — |
Knowledge Claude Opus 4.7 leads
Claude Opus 4.7: 62.6 (#20), Grok 4.20 Multi-Agent: 39.7 (#116)
| Benchmark | Claude Opus 4.7 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Expert | 1521 | 1445 |
| GPQA Diamond | 90.2% | — |
| Humanity's Last Exam | 36.2% | — |
| SimpleQA Verified | 51.7% | — |
| Vectara Hallucination Rate | 12% | — |
Multimodal Claude Opus 4.7 leads
Claude Opus 4.7: 41.5 (#29), Grok 4.20 Multi-Agent: 39.8 (#44)
| Benchmark | Claude Opus 4.7 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Vision | 1317 | 1259 |
| Blueprint-Bench 2 | 24.5% | — |
| Furniture Assembly | 33.3% | — |
| LMArena Document | 1495 | — |
Multilingual Claude Opus 4.7 leads
Claude Opus 4.7: 57.5 (#9), Grok 4.20 Multi-Agent: 54.6 (#40)
| Benchmark | Claude Opus 4.7 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Non-English | 1481 | 1440 |
| LMArena Chinese | 1530 | 1475 |
| LMArena French | 1505 | 1467 |
| LMArena German | 1494 | 1456 |
| LMArena Japanese | 1472 | 1405 |
| LMArena Korean | 1466 | 1416 |
| LMArena Russian | 1494 | 1457 |
| LMArena Spanish | 1497 | 1447 |
Instruction Following Claude Opus 4.7 leads
Claude Opus 4.7: 78.6 (#9), Grok 4.20 Multi-Agent: 75.0 (#80)
| Benchmark | Claude Opus 4.7 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Instruction Following | 1498 | 1420 |
Long Context Claude Opus 4.7 leads
Claude Opus 4.7: 46.1 (#24), Grok 4.20 Multi-Agent: 43.7 (#84)
| Benchmark | Claude Opus 4.7 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Longer Query | 1505 | 1430 |
Writing & Preference Claude Opus 4.7 leads
Claude Opus 4.7: 75.3 (#8), Grok 4.20 Multi-Agent: 64.1 (#57)
| Benchmark | Claude Opus 4.7 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Text | 1491 | 1450 |
| LMArena Creative Writing | 1486 | 1435 |
| LMArena Multi-Turn | 1506 | 1451 |
| EQ-Bench Creative Writing | 1914 | — |
| EQ-Bench 4 | 1311 | — |
Frequently asked questions
Is Claude Opus 4.7 better than Grok 4.20 Multi-Agent?
Claude Opus 4.7 is the stronger model overall, scoring 58.4 to 45.5 on the Noometry Index. Grok 4.20 Multi-Agent 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 Multi-Agent?
Grok 4.20 Multi-Agent 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 Multi-Agent better for coding?
Claude Opus 4.7 scores higher on coding benchmarks: 59.9 versus 42.4 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 Multi-Agent share?
20 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and Grok 4.20 Multi-Agent has 20.