Model comparison
Claude Sonnet 4.6 vs Grok 4.3
Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 43.8 on the Noometry Index. Grok 4.3 costs 3.8× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.
Last verified . 38 shared benchmarks.
Summary
- They share 38 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 9 categories and Grok 4.3 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Sonnet 4.6 leads 70.2 to 58.5.
- The biggest single-benchmark swing is ProofBench: 45% for Claude Sonnet 4.6 and 11% for Grok 4.3.
- Grok 4.3 is cheaper at $1.25 / $2.50 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
Side by side
| Claude Sonnet 4.6 | Grok 4.3 | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 50.3 | 43.8 |
| Released | 2026-02-17 | 2026-04-17 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1M |
| Max output | 128K | 30K |
| Input $ / M tokens | $3 | $1.25 |
| Output $ / M tokens | $15 | $2.50 |
| Results tracked | 57 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 46.3 (#67), Grok 4.3: 41.6 (#121)
| Benchmark | Claude Sonnet 4.6 | Grok 4.3 |
|---|---|---|
| LMArena WebDev | 1522 | 1357 |
| SciCode | 46.8% | 47.3% |
| WeirdML | 66.1% | 49.9% |
| LMArena Coding | 1504 | 1415 |
| ALE-Bench | 1,327 | 944.17 |
| SWE-bench Verified | 75.2% | — |
| DeepSWE | 29.9% | — |
| FrontierCode | 24.3% | — |
Agentic & Tool Use Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 39.1 (#28), Grok 4.3: 27.7 (#99)
| Benchmark | Claude Sonnet 4.6 | Grok 4.3 |
|---|---|---|
| GDP.pdf | 18% | 8% |
| LMArena Search | 1221 | 1165 |
| Vending-Bench 2 | 7,204 | 35.26 |
| Terminal-Bench | 53.4% | — |
| APEX-Agents | 43% | — |
| OSWorld 2.0 | 9.3% | — |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
Reasoning Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 46.1 (#45), Grok 4.3: 35.9 (#68)
| Benchmark | Claude Sonnet 4.6 | Grok 4.3 |
|---|---|---|
| NYT Connections (extended) | 80.9% | 55.2% |
| CritPt | 3.1% | 8% |
| Chess Puzzles | 13% | 25% |
| LMArena Hard Prompts | 1484 | 1396 |
| DTBench | 89.9% | 90.7% |
| LMCA | 46.5% | 38.3% |
| Epoch Capabilities Index | 152.24 | 149.16 |
| ForecastBench | 62 | 60.3 |
| ARC-AGI-2 | 60.4% | — |
| ARC-AGI-1 | 86.5% | — |
| Thematic Generalization | 76.3% | — |
| Mystery Game Puzzles | 16% | — |
Math Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 52.9 (#49), Grok 4.3: 46.0 (#74)
| Benchmark | Claude Sonnet 4.6 | Grok 4.3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | 93.3% |
| ProofBench | 45% | 11% |
| LMArena Math | 1462 | 1388 |
| FrontierMath (Tiers 1-3) | — | 42.8% |
| FrontierMath Tier 4 | — | 14.6% |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |
Knowledge Too close to call
Claude Sonnet 4.6: 51.7 (#65), Grok 4.3: 52.5 (#62)
| Benchmark | Claude Sonnet 4.6 | Grok 4.3 |
|---|---|---|
| GPQA Diamond | 87.4% | 88.8% |
| SimpleQA Verified | 35.5% | 33.2% |
| LMArena Expert | 1500 | 1385 |
| Vectara Hallucination Rate | 10.6% | — |
Multimodal Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 38.0 (#68), Grok 4.3: 31.6 (#104)
| Benchmark | Claude Sonnet 4.6 | Grok 4.3 |
|---|---|---|
| LMArena Vision | 1283 | 1229 |
| Blueprint-Bench 2 | 6.7% | 0% |
| LMArena Document | 1482 | — |
Multilingual Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 54.4 (#41), Grok 4.3: 50.5 (#120)
| Benchmark | Claude Sonnet 4.6 | Grok 4.3 |
|---|---|---|
| LMArena Non-English | 1440 | 1385 |
| LMArena Chinese | 1491 | 1422 |
| LMArena French | 1465 | 1412 |
| LMArena German | 1428 | 1395 |
| LMArena Japanese | 1420 | 1379 |
| LMArena Korean | 1411 | 1356 |
| LMArena Russian | 1440 | 1399 |
| LMArena Spanish | 1464 | 1398 |
Instruction Following Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 77.4 (#25), Grok 4.3: 72.1 (#140)
| Benchmark | Claude Sonnet 4.6 | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | 1475 | 1366 |
Long Context Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 45.3 (#44), Grok 4.3: 42.5 (#123)
| Benchmark | Claude Sonnet 4.6 | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | 1479 | 1393 |
Writing & Preference Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 70.2 (#22), Grok 4.3: 58.5 (#118)
| Benchmark | Claude Sonnet 4.6 | Grok 4.3 |
|---|---|---|
| LMArena Text | 1458 | 1397 |
| LMArena Creative Writing | 1435 | 1380 |
| EQ-Bench 4 | 1207 | 1075 |
| LMArena Multi-Turn | 1464 | 1406 |
| EQ-Bench Creative Writing | 1810 | — |
Frequently asked questions
Is Claude Sonnet 4.6 better than Grok 4.3?
Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 43.8 on the Noometry Index. Grok 4.3 costs 3.8× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 4.6 or Grok 4.3?
Grok 4.3 is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.
Is Claude Sonnet 4.6 or Grok 4.3 better for coding?
Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 41.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Sonnet 4.6 and Grok 4.3 share?
38 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Grok 4.3 has 40.