Model comparison
Claude Opus 4.6 vs Grok 4
Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 48.1 on the Noometry Index.
Last verified . 35 shared benchmarks.
Summary
- They share 35 benchmarks with published results for both. Claude Opus 4.6 scores higher in 9 categories and Grok 4 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 4.6 leads 57.8 to 36.7.
- The biggest single-benchmark swing is ARC-AGI-2: 69.2% for Claude Opus 4.6 and 16% for Grok 4.
Side by side
| Claude Opus 4.6 | Grok 4 | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 58.2 | 48.1 |
| Released | 2026-02-04 | 2025-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $5 | — |
| Output $ / M tokens | $25 | — |
| Results tracked | 68 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.6 leads
Claude Opus 4.6: 57.2 (#20), Grok 4: 50.3 (#46)
| Benchmark | Claude Opus 4.6 | Grok 4 |
|---|---|---|
| WeirdML | 78% | 45.7% |
| LMArena Coding | 1536 | 1408 |
| SWE-bench Verified | 78.7% | — |
| FrontierCode | 26.6% | — |
| SWE-bench Verified (bash only) | 75.6% | — |
| Aider Polyglot | — | 79.6% |
| LMArena WebDev | 1547 | — |
| SWE-bench Multilingual | 72% | — |
| GSO | 41.2% | — |
| ALE-Bench | 996.5 | — |
| AlgoTune | 1.47 | — |
Agentic & Tool Use Claude Opus 4.6 leads
Claude Opus 4.6: 51.1 (#4), Grok 4: 32.3 (#68)
| Benchmark | Claude Opus 4.6 | Grok 4 |
|---|---|---|
| Terminal-Bench | 79.8% | 27.2% |
| Cybench | 93% | 43% |
| DeepResearch Bench | 55.3% | 47.3% |
| LMArena Search | 1253 | 1142 |
| METR Time Horizons | 78.9% | 66.6% |
| APEX-Agents | 46.3% | — |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| Remote Labor Index | 4.2% | — |
| τ²-bench Banking | 27.3% | — |
| BALROG | — | 43.6% |
| GBAEval | 44.1% | — |
| Vending-Bench 2 | 8,018 | — |
Reasoning Claude Opus 4.6 leads
Claude Opus 4.6: 57.8 (#23), Grok 4: 36.7 (#65)
| Benchmark | Claude Opus 4.6 | Grok 4 |
|---|---|---|
| ARC-AGI-2 | 69.2% | 16% |
| SimpleBench | 67.6% | 60.5% |
| Kagi LLM Benchmark | 83.6% | 73.6% |
| ARC-AGI-1 | 94% | 66.7% |
| Chess Puzzles | 17% | 28% |
| LMArena Hard Prompts | 1527 | 1409 |
| Epoch Capabilities Index | 155.24 | 146.44 |
| ForecastBench | 60 | 60.9 |
| NYT Connections (extended) | 92.1% | — |
| EnigmaEval | 7.6% | — |
| Thematic Generalization | 80.6% | — |
| EBR-Bench | 12.7% | — |
| Mystery Game Puzzles | 25% | — |
| DTBench | 91.2% | — |
| LMCA | 55.8% | — |
Math Claude Opus 4.6 leads
Claude Opus 4.6: 63.0 (#31), Grok 4: 48.4 (#64)
| Benchmark | Claude Opus 4.6 | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.4% | 84% |
| LMArena Math | 1519 | 1422 |
| FrontierMath (Feb 2025 set) | 40.7% | 19.7% |
| FrontierMath Tier 4 (v1) | 22.9% | 2.1% |
| FrontierMath (Tiers 1-3) | 66% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 78.5% | — |
| ProofBench | 50% | — |
| Omni-MATH | — | 60.3% |
Knowledge Claude Opus 4.6 leads
Claude Opus 4.6: 61.9 (#26), Grok 4: 53.8 (#55)
| Benchmark | Claude Opus 4.6 | Grok 4 |
|---|---|---|
| GPQA Diamond | 90.5% | 87% |
| LMArena Expert | 1546 | 1415 |
| Humanity's Last Exam | 34.4% | — |
| SimpleQA Verified | 47% | — |
| MMLU-Pro | — | 85.1% |
| Confabulations | — | 12.4% |
| Vectara Hallucination Rate | 12.2% | — |
| GPQA (HELM) | — | 72.7% |
Multimodal Claude Opus 4.6 leads
Claude Opus 4.6: 37.3 (#74), Grok 4: 33.7 (#94)
| Benchmark | Claude Opus 4.6 | Grok 4 |
|---|---|---|
| LMArena Vision | 1316 | 1210 |
| GeoBench | — | 45% |
| Furniture Assembly | 28.3% | — |
| LMArena Document | 1507 | — |
Multilingual Claude Opus 4.6 leads
Claude Opus 4.6: 57.9 (#6), Grok 4: 51.8 (#103)
| Benchmark | Claude Opus 4.6 | Grok 4 |
|---|---|---|
| LMArena Non-English | 1489 | 1403 |
| LMArena Chinese | 1551 | 1427 |
| LMArena French | 1513 | 1418 |
| LMArena German | 1502 | 1429 |
| LMArena Japanese | 1484 | 1394 |
| LMArena Korean | 1464 | 1377 |
| LMArena Russian | 1497 | 1410 |
| LMArena Spanish | 1510 | 1420 |
Instruction Following Too close to call
Claude Opus 4.6: 79.5 (#4), Grok 4: 79.2 (#5)
| Benchmark | Claude Opus 4.6 | Grok 4 |
|---|---|---|
| LMArena Instruction Following | 1523 | 1387 |
| IFEval | — | 94.9% |
Long Context Grok 4 leads
Claude Opus 4.6: 48.1 (#13), Grok 4: 63.1 (#4)
| Benchmark | Claude Opus 4.6 | Grok 4 |
|---|---|---|
| LMArena Longer Query | 1520 | 1409 |
| Fiction.LiveBench | — | 94.4% |
| CL-bench | 20.7% | — |
| CL-bench Life | 17% | — |
Writing & Preference Claude Opus 4.6 leads
Claude Opus 4.6: 73.5 (#10), Grok 4: 58.5 (#116)
| Benchmark | Claude Opus 4.6 | Grok 4 |
|---|---|---|
| LMArena Text | 1503 | 1411 |
| LMArena Creative Writing | 1505 | 1397 |
| LMArena Multi-Turn | 1513 | 1416 |
| Short-Story Creative Writing | — | 76.9% |
| EQ-Bench Creative Writing | 1809 | — |
| WildBench | — | 79.7% |
| EQ-Bench 4 | 1223 | — |
Frequently asked questions
Is Claude Opus 4.6 better than Grok 4?
Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 48.1 on the Noometry Index.
Is Claude Opus 4.6 or Grok 4 better for coding?
Claude Opus 4.6 scores higher on coding benchmarks: 57.2 versus 50.3 in the Noometry coding category.
How many benchmarks do Claude Opus 4.6 and Grok 4 share?
35 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and Grok 4 has 48.