Model comparison
Claude 3 Opus vs Grok 4.6
Grok 4.6 is the stronger model overall, scoring 56.9 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 4.6 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4.6 leads 67.0 to 14.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 99.2% for Grok 4.6.
Side by side
| Claude 3 Opus | Grok 4.6 | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 29.5 | 56.9 |
| Released | 2024-02-29 | 2026-08-12 |
| Weights | Proprietary | Proprietary |
| Context window | — | 500K |
| Max output | — | 500K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 46 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
Claude 3 Opus: 32.9 (#267), Grok 4.6: 58.5 (#16)
| Benchmark | Claude 3 Opus | Grok 4.6 |
|---|---|---|
| WeirdML | 19.2% | 67.3% |
| LMArena Coding | 1264 | 1465 |
| DeepSWE | — | 67.5% |
| FrontierCode | — | 48% |
| CursorBench | — | 41.4% |
| LMArena WebDev | — | 1617 |
| FrontierSWE | — | 25.3% |
| SciCode | — | 56.5% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 1,508 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Grok 4.6 leads
Claude 3 Opus: 24.6 (#116), Grok 4.6: 39.4 (#27)
| Benchmark | Claude 3 Opus | Grok 4.6 |
|---|---|---|
| APEX-Agents | — | 65.3% |
| Cybench | 10% | — |
| GDP.pdf | — | 17.2% |
| METR Time Horizons | 29.5% | — |
| Vending-Bench 2 | — | 9,047 |
Reasoning Grok 4.6 leads
Claude 3 Opus: 14.6 (#324), Grok 4.6: 61.4 (#20)
| Benchmark | Claude 3 Opus | Grok 4.6 |
|---|---|---|
| SimpleBench | 23.5% | 75.9% |
| Chess Puzzles | 5% | 40% |
| LMArena Hard Prompts | 1245 | 1447 |
| DTBench | 61.6% | 97.3% |
| LMCA | 17% | 48.5% |
| Epoch Capabilities Index | 126.91 | 156.44 |
| ARC-AGI-2 | — | 67.1% |
| NYT Connections (extended) | — | 80% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 19.7% |
| EnigmaEval | 0.8% | — |
| EBR-Bench | — | 30.5% |
| LiveBench Reasoning | 40.6% | — |
| Mystery Game Puzzles | — | 34% |
| LiveBench Data Analysis | 57.9% | — |
| ForecastBench | 58.4 | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Grok 4.6 leads
Claude 3 Opus: 14.8 (#299), Grok 4.6: 67.0 (#24)
| Benchmark | Claude 3 Opus | Grok 4.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 99.2% |
| LMArena Math | 1273 | 1423 |
| FrontierMath (Tiers 1-3) | — | 66% |
| FrontierMath Tier 4 | — | 31.7% |
| ProofBench | — | 51% |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
Knowledge Grok 4.6 leads
Claude 3 Opus: 24.5 (#267), Grok 4.6: 63.3 (#20)
| Benchmark | Claude 3 Opus | Grok 4.6 |
|---|---|---|
| GPQA Diamond | 47.2% | 94% |
| SimpleQA Verified | 12.6% | 49.3% |
| LMArena Expert | 1223 | 1467 |
| Confabulations | 22.7% | — |
| MMLU | 84.6% | — |
Multimodal Grok 4.6 leads
Claude 3 Opus: 27.1 (#116), Grok 4.6: 43.6 (#23)
| Benchmark | Claude 3 Opus | Grok 4.6 |
|---|---|---|
| LMArena Vision | 1023 | 1263 |
| Blueprint-Bench 2 | — | 33.2% |
| Furniture Assembly | — | 40% |
| LMArena Document | — | 1452 |
Multilingual Grok 4.6 leads
Claude 3 Opus: 41.4 (#207), Grok 4.6: 53.0 (#74)
| Benchmark | Claude 3 Opus | Grok 4.6 |
|---|---|---|
| LMArena Non-English | 1258 | 1420 |
| LMArena Chinese | 1248 | 1480 |
| LMArena French | 1275 | 1461 |
| LMArena German | 1258 | 1431 |
| LMArena Japanese | 1204 | 1376 |
| LMArena Korean | 1187 | 1397 |
| LMArena Russian | 1280 | 1422 |
| LMArena Spanish | 1246 | 1404 |
Instruction Following Grok 4.6 leads
Claude 3 Opus: 64.1 (#228), Grok 4.6: 75.4 (#63)
| Benchmark | Claude 3 Opus | Grok 4.6 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1431 |
| LiveBench Instruction Following | 63.9% | — |
Long Context Grok 4.6 leads
Claude 3 Opus: 38.2 (#202), Grok 4.6: 44.5 (#66)
| Benchmark | Claude 3 Opus | Grok 4.6 |
|---|---|---|
| LMArena Longer Query | 1259 | 1454 |
Writing & Preference Grok 4.6 leads
Claude 3 Opus: 47.2 (#213), Grok 4.6: 62.3 (#80)
| Benchmark | Claude 3 Opus | Grok 4.6 |
|---|---|---|
| LMArena Text | 1262 | 1428 |
| LMArena Creative Writing | 1235 | 1428 |
| LMArena Multi-Turn | 1275 | 1425 |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Grok 4.6?
Grok 4.6 is the stronger model overall, scoring 56.9 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Grok 4.6 better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Grok 4.6 share?
27 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Grok 4.6 has 49.