Model comparison
Claude 3.5 Sonnet vs Grok 4.20 (Non-Reasoning)
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 34.6 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 0 categories and Grok 4.20 (Non-Reasoning) in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 23.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 92.2% for Grok 4.20 (Non-Reasoning).
Side by side
| Claude 3.5 Sonnet | Grok 4.20 (Non-Reasoning) | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 34.6 | 48.6 |
| Released | 2024-06-20 | 2026-02-17 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 30K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 60 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 (Non-Reasoning) leads
Claude 3.5 Sonnet: 39.0 (#165), Grok 4.20 (Non-Reasoning): 42.1 (#112)
| Benchmark | Claude 3.5 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| WeirdML | 40% | 52.3% |
| LMArena Coding | 1342 | 1459 |
| Aider Polyglot | 51.6% | — |
| LMArena WebDev | — | 1375 |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| ALE-Bench | — | 1,150 |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Grok 4.20 (Non-Reasoning) leads
Claude 3.5 Sonnet: 32.3 (#67), Grok 4.20 (Non-Reasoning): 34.4 (#46)
| Benchmark | Claude 3.5 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | — | 57.3% |
| TheAgentCompany | 24% | — |
| τ²-bench Banking | — | 18% |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| LMArena Search | — | 1189 |
| METR Time Horizons | 45.2% | — |
| Vending-Bench 2 | — | 4,663 |
Reasoning Grok 4.20 (Non-Reasoning) leads
Claude 3.5 Sonnet: 23.1 (#183), Grok 4.20 (Non-Reasoning): 52.3 (#32)
| Benchmark | Claude 3.5 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1451 |
| DTBench | 67.8% | 90.1% |
| Epoch Capabilities Index | 133.55 | 151.98 |
| ForecastBench | 60.7 | 61.4 |
| ARC-AGI-2 | — | 65.1% |
| SimpleBench | 41.4% | — |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 85.4% |
| ARC-AGI-1 | — | 89.5% |
| Chess Puzzles | — | 24% |
| EnigmaEval | 0.9% | — |
| Thematic Generalization | — | 63.8% |
| LiveBench Reasoning | 56.7% | — |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 38.7% |
| LiveBench | 59% | — |
Math Grok 4.20 (Non-Reasoning) leads
Claude 3.5 Sonnet: 19.2 (#288), Grok 4.20 (Non-Reasoning): 48.2 (#65)
| Benchmark | Claude 3.5 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 92.2% |
| LMArena Math | 1307 | 1455 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 14% |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 4.20 (Non-Reasoning) leads
Claude 3.5 Sonnet: 28.6 (#245), Grok 4.20 (Non-Reasoning): 52.8 (#60)
| Benchmark | Claude 3.5 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 55.3% | 89.3% |
| LMArena Expert | 1265 | 1439 |
| Humanity's Last Exam | 4.1% | — |
| SimpleQA Verified | — | 30.2% |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Grok 4.20 (Non-Reasoning) leads
Claude 3.5 Sonnet: 26.5 (#120), Grok 4.20 (Non-Reasoning): 33.3 (#98)
| Benchmark | Claude 3.5 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | 1125 | 1263 |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |
Multilingual Grok 4.20 (Non-Reasoning) leads
Claude 3.5 Sonnet: 43.2 (#185), Grok 4.20 (Non-Reasoning): 54.5 (#40)
| Benchmark | Claude 3.5 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1283 | 1441 |
| LMArena Chinese | 1272 | 1481 |
| LMArena French | 1305 | 1476 |
| LMArena German | 1297 | 1465 |
| LMArena Japanese | 1234 | 1449 |
| LMArena Korean | 1200 | 1417 |
| LMArena Russian | 1306 | 1458 |
| LMArena Spanish | 1290 | 1443 |
Instruction Following Grok 4.20 (Non-Reasoning) leads
Claude 3.5 Sonnet: 68.8 (#182), Grok 4.20 (Non-Reasoning): 74.8 (#83)
| Benchmark | Claude 3.5 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1297 | 1420 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context Grok 4.20 (Non-Reasoning) leads
Claude 3.5 Sonnet: 39.9 (#167), Grok 4.20 (Non-Reasoning): 45.5 (#34)
| Benchmark | Claude 3.5 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1311 | 1437 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
Claude 3.5 Sonnet: 52.9 (#164), Grok 4.20 (Non-Reasoning): 65.7 (#44)
| Benchmark | Claude 3.5 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1298 | 1451 |
| LMArena Creative Writing | 1292 | 1438 |
| EQ-Bench Creative Writing | 1451 | 1574 |
| LMArena Multi-Turn | 1326 | 1456 |
| Short-Story Creative Writing | 80.3% | — |
| WildBench | 79.2% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Grok 4.20 (Non-Reasoning)?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or Grok 4.20 (Non-Reasoning) better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 39.0 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Grok 4.20 (Non-Reasoning) share?
25 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.