Model comparison
Claude 3 Opus vs Grok 4.20 (Non-Reasoning)
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 29.5 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. Claude 3 Opus 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 14.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 92.2% for Grok 4.20 (Non-Reasoning).
Side by side
| Claude 3 Opus | Grok 4.20 (Non-Reasoning) | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 29.5 | 48.6 |
| Released | 2024-02-29 | 2026-02-17 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 30K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 46 | 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 Opus: 32.9 (#267), Grok 4.20 (Non-Reasoning): 42.1 (#112)
| Benchmark | Claude 3 Opus | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| WeirdML | 19.2% | 52.3% |
| LMArena Coding | 1264 | 1459 |
| LMArena WebDev | — | 1375 |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 1,150 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Grok 4.20 (Non-Reasoning) leads
Claude 3 Opus: 24.6 (#116), Grok 4.20 (Non-Reasoning): 34.4 (#46)
| Benchmark | Claude 3 Opus | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | — | 57.3% |
| τ²-bench Banking | — | 18% |
| Cybench | 10% | — |
| LMArena Search | — | 1189 |
| METR Time Horizons | 29.5% | — |
| Vending-Bench 2 | — | 4,663 |
Reasoning Grok 4.20 (Non-Reasoning) leads
Claude 3 Opus: 14.6 (#324), Grok 4.20 (Non-Reasoning): 52.3 (#32)
| Benchmark | Claude 3 Opus | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Chess Puzzles | 5% | 24% |
| LMArena Hard Prompts | 1245 | 1451 |
| DTBench | 61.6% | 90.1% |
| LMCA | 17% | 38.7% |
| Epoch Capabilities Index | 126.91 | 151.98 |
| ForecastBench | 58.4 | 61.4 |
| ARC-AGI-2 | — | 65.1% |
| SimpleBench | 23.5% | — |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 85.4% |
| ARC-AGI-1 | — | 89.5% |
| EnigmaEval | 0.8% | — |
| Thematic Generalization | — | 63.8% |
| LiveBench Reasoning | 40.6% | — |
| LiveBench Data Analysis | 57.9% | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Grok 4.20 (Non-Reasoning) leads
Claude 3 Opus: 14.8 (#299), Grok 4.20 (Non-Reasoning): 48.2 (#65)
| Benchmark | Claude 3 Opus | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 92.2% |
| LMArena Math | 1273 | 1455 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 14% |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
Knowledge Grok 4.20 (Non-Reasoning) leads
Claude 3 Opus: 24.5 (#267), Grok 4.20 (Non-Reasoning): 52.8 (#60)
| Benchmark | Claude 3 Opus | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 47.2% | 89.3% |
| SimpleQA Verified | 12.6% | 30.2% |
| LMArena Expert | 1223 | 1439 |
| Confabulations | 22.7% | — |
| MMLU | 84.6% | — |
Multimodal Grok 4.20 (Non-Reasoning) leads
Claude 3 Opus: 27.1 (#116), Grok 4.20 (Non-Reasoning): 33.3 (#98)
| Benchmark | Claude 3 Opus | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | 1023 | 1263 |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |
Multilingual Grok 4.20 (Non-Reasoning) leads
Claude 3 Opus: 41.4 (#207), Grok 4.20 (Non-Reasoning): 54.5 (#40)
| Benchmark | Claude 3 Opus | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1258 | 1441 |
| LMArena Chinese | 1248 | 1481 |
| LMArena French | 1275 | 1476 |
| LMArena German | 1258 | 1465 |
| LMArena Japanese | 1204 | 1449 |
| LMArena Korean | 1187 | 1417 |
| LMArena Russian | 1280 | 1458 |
| LMArena Spanish | 1246 | 1443 |
Instruction Following Grok 4.20 (Non-Reasoning) leads
Claude 3 Opus: 64.1 (#228), Grok 4.20 (Non-Reasoning): 74.8 (#83)
| Benchmark | Claude 3 Opus | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1248 | 1420 |
| LiveBench Instruction Following | 63.9% | — |
Long Context Grok 4.20 (Non-Reasoning) leads
Claude 3 Opus: 38.2 (#202), Grok 4.20 (Non-Reasoning): 45.5 (#34)
| Benchmark | Claude 3 Opus | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1259 | 1437 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
Claude 3 Opus: 47.2 (#213), Grok 4.20 (Non-Reasoning): 65.7 (#44)
| Benchmark | Claude 3 Opus | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1262 | 1451 |
| LMArena Creative Writing | 1235 | 1438 |
| LMArena Multi-Turn | 1275 | 1456 |
| EQ-Bench Creative Writing | — | 1574 |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Grok 4.20 (Non-Reasoning)?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Grok 4.20 (Non-Reasoning) better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Grok 4.20 (Non-Reasoning) share?
27 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.