Model comparison
Claude Sonnet 4.5 vs Grok 4.7
Grok 4.7 is the stronger model overall, scoring 53.1 to 44.1 on the Noometry Index.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 4 categories and Grok 4.7 in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4.7 leads 57.8 to 32.3.
- The biggest single-benchmark swing is NYT Connections (extended): 37.3% for Claude Sonnet 4.5 and 76.8% for Grok 4.7.
- Grok 4.7 is cheaper at $2 / $6 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
- Grok 4.7 accepts more context: 500K tokens versus 200K.
Side by side
| Claude Sonnet 4.5 | Grok 4.7 | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 44.1 | 53.1 |
| Released | 2025-09-29 | 2026-09-21 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 500K |
| Max output | 64K | 500K |
| Input $ / M tokens | $3 | $2 |
| Output $ / M tokens | $15 | $6 |
| Results tracked | 73 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.7 leads
Claude Sonnet 4.5: 47.3 (#61), Grok 4.7: 58.0 (#18)
| Benchmark | Claude Sonnet 4.5 | Grok 4.7 |
|---|---|---|
| LMArena WebDev | 1393 | 1639 |
| SciCode | 44.7% | 57.8% |
| LMArena Coding | 1489 | 1427 |
| SWE-bench Verified | 71.3% | — |
| FrontierCode | — | 47.6% |
| SWE-bench Verified (bash only) | 71.4% | — |
| CursorBench | — | 46.3% |
| SWE-bench Multilingual | 67% | — |
| FrontierSWE | — | 29.5% |
| GSO | 14.7% | — |
| WeirdML | 47.7% | — |
| ALE-Bench | 796.15 | — |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 38.3 (#32), Grok 4.7: 36.7 (#37)
| Benchmark | Claude Sonnet 4.5 | Grok 4.7 |
|---|---|---|
| Vending-Bench 2 | 3,839 | 10,537 |
| Terminal-Bench | 46.5% | — |
| APEX-Agents | — | 54.6% |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| GDP.pdf | — | 22.8% |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
Reasoning Grok 4.7 leads
Claude Sonnet 4.5: 26.9 (#125), Grok 4.7: 49.1 (#40)
| Benchmark | Claude Sonnet 4.5 | Grok 4.7 |
|---|---|---|
| NYT Connections (extended) | 37.3% | 76.8% |
| CritPt | 1.1% | 18% |
| Chess Puzzles | 12% | 38% |
| LMArena Hard Prompts | 1462 | 1413 |
| Mystery Game Puzzles | 17% | 29% |
| DTBench | 83.2% | 96% |
| LMCA | 38.8% | 49.4% |
| Epoch Capabilities Index | 146.84 | 153.53 |
| ARC-AGI-2 | 13.6% | — |
| SimpleBench | 54.3% | — |
| Kagi LLM Benchmark | 57.9% | — |
| ARC-AGI-1 | 63.7% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |
| ForecastBench | 61.9 | — |
Math Grok 4.7 leads
Claude Sonnet 4.5: 32.3 (#216), Grok 4.7: 57.8 (#39)
| Benchmark | Claude Sonnet 4.5 | Grok 4.7 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 23.9% | 53% |
| FrontierMath Tier 4 | 2.4% | 17.1% |
| OTIS Mock AIME 2024-2025 | 77.8% | 98.1% |
| ProofBench | 19% | 34% |
| LMArena Math | 1449 | 1407 |
| Omni-MATH | 55.3% | — |
| MATH Level 5 | 97.7% | — |
| FrontierMath (Feb 2025 set) | 15.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Grok 4.7 leads
Claude Sonnet 4.5: 48.4 (#76), Grok 4.7: 62.8 (#22)
| Benchmark | Claude Sonnet 4.5 | Grok 4.7 |
|---|---|---|
| GPQA Diamond | 82.3% | 92.7% |
| SimpleQA Verified | 30.7% | 56% |
| LMArena Expert | 1482 | 1422 |
| Humanity's Last Exam | 13.7% | — |
| MMLU-Pro | 86.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 68.6% | — |
Multimodal Too close to call
Claude Sonnet 4.5: 34.8 (#89), Grok 4.7: 35.5 (#87)
| Benchmark | Claude Sonnet 4.5 | Grok 4.7 |
|---|---|---|
| LMArena Vision | — | 1228 |
| VPCT | 39.8% | — |
| Blueprint-Bench 2 | — | 32.5% |
| Furniture Assembly | — | 20.8% |
| LMArena Document | 1450 | — |
Multilingual Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 53.4 (#69), Grok 4.7: 50.8 (#116)
| Benchmark | Claude Sonnet 4.5 | Grok 4.7 |
|---|---|---|
| LMArena Non-English | 1425 | 1389 |
| LMArena Chinese | 1459 | 1455 |
| LMArena French | 1458 | 1455 |
| LMArena Russian | 1437 | 1397 |
| LMArena Spanish | 1457 | 1400 |
| LMArena German | 1427 | — |
| LMArena Japanese | 1390 | — |
| LMArena Korean | 1403 | — |
Instruction Following Too close to call
Claude Sonnet 4.5: 75.0 (#78), Grok 4.7: 74.1 (#105)
| Benchmark | Claude Sonnet 4.5 | Grok 4.7 |
|---|---|---|
| LMArena Instruction Following | 1459 | 1404 |
| IFEval | 85% | — |
Long Context Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 45.2 (#46), Grok 4.7: 43.1 (#104)
| Benchmark | Claude Sonnet 4.5 | Grok 4.7 |
|---|---|---|
| LMArena Longer Query | 1476 | 1413 |
Writing & Preference Grok 4.7 leads
Claude Sonnet 4.5: 66.5 (#34), Grok 4.7: 70.0 (#24)
| Benchmark | Claude Sonnet 4.5 | Grok 4.7 |
|---|---|---|
| LMArena Text | 1439 | 1399 |
| LMArena Creative Writing | 1442 | 1391 |
| EQ-Bench Creative Writing | 1678 | 2007 |
| LMArena Multi-Turn | 1465 | 1393 |
| WildBench | 85.4% | — |
Frequently asked questions
Is Claude Sonnet 4.5 better than Grok 4.7?
Grok 4.7 is the stronger model overall, scoring 53.1 to 44.1 on the Noometry Index.
Which is cheaper, Claude Sonnet 4.5 or Grok 4.7?
Grok 4.7 is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.
Is Claude Sonnet 4.5 or Grok 4.7 better for coding?
Grok 4.7 scores higher on coding benchmarks: 58.0 versus 47.3 in the Noometry coding category.
Which has the bigger context window?
Grok 4.7 does, with 500K tokens against 200K.
How many benchmarks do Claude Sonnet 4.5 and Grok 4.7 share?
31 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Grok 4.7 has 39.