Model comparison
Claude Opus 4.6 vs Grok 4.20 Multi-Agent
Claude Opus 4.6 is the stronger model overall, scoring 58.3 to 45.5 on the Noometry Index. Grok 4.20 Multi-Agent costs 6.4× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. Claude Opus 4.6 scores higher in 8 categories and Grok 4.20 Multi-Agent in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4.6 leads 62.7 to 36.6.
- Grok 4.20 Multi-Agent is cheaper at $1.25 / $2.50 per million input/output tokens, against $5 / $25 for Claude Opus 4.6.
Side by side
| Claude Opus 4.6 | Grok 4.20 Multi-Agent | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 58.3 | 45.5 |
| Released | 2026-02-04 | 2026-03-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1M |
| Max output | 128K | 30K |
| Input $ / M tokens | $5 | $1.25 |
| Output $ / M tokens | $25 | $2.50 |
| Results tracked | 68 | 20 |
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: 57.7 (#15), Grok 4.20 Multi-Agent: 42.4 (#91)
| Benchmark | Claude Opus 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Coding | 1535 | 1458 |
| SWE-bench Verified | 78.7% | — |
| FrontierCode | 26.6% | — |
| SWE-bench Verified (bash only) | 75.6% | — |
| LMArena WebDev | 1546 | — |
| SWE-bench Multilingual | 72% | — |
| GSO | 41.2% | — |
| WeirdML | 78% | — |
| ALE-Bench | 996.5 | — |
| AlgoTune | 1.47 | — |
Agentic & Tool Use Not comparable
Claude Opus 4.6: 51.0 (#4), Grok 4.20 Multi-Agent: —
| Benchmark | Claude Opus 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Search | 1253 | 1204 |
| Terminal-Bench | 79.8% | — |
| APEX-Agents | 46.3% | — |
| Remote Labor Index | 4.2% | — |
| τ²-bench Banking | 27.3% | — |
| Cybench | 93% | — |
| DeepResearch Bench | 55.3% | — |
| GBAEval | 44.1% | — |
| METR Time Horizons | 78.9% | — |
| Vending-Bench 2 | 8,018 | — |
Reasoning Claude Opus 4.6 leads
Claude Opus 4.6: 57.7 (#21), Grok 4.20 Multi-Agent: 42.4 (#44)
| Benchmark | Claude Opus 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| NYT Connections (extended) | 92.1% | 89.6% |
| LMArena Hard Prompts | 1527 | 1448 |
| ARC-AGI-2 | 69.2% | — |
| SimpleBench | 67.6% | — |
| Kagi LLM Benchmark | 83.6% | — |
| ARC-AGI-1 | 94% | — |
| Chess Puzzles | 17% | — |
| EnigmaEval | 7.6% | — |
| Thematic Generalization | 80.6% | — |
| EBR-Bench | 12.7% | — |
| Mystery Game Puzzles | 25% | — |
| DTBench | 91.2% | — |
| LMCA | 55.8% | — |
| Epoch Capabilities Index | 155.36 | — |
| ForecastBench | 60 | — |
Math Claude Opus 4.6 leads
Claude Opus 4.6: 62.7 (#25), Grok 4.20 Multi-Agent: 36.6 (#106)
| Benchmark | Claude Opus 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Math | 1517 | 1441 |
| FrontierMath (Tiers 1-3) | 66% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 78.5% | — |
| OTIS Mock AIME 2024-2025 | 94.4% | — |
| ProofBench | 50% | — |
| FrontierMath (Feb 2025 set) | 40.7% | — |
| FrontierMath Tier 4 (v1) | 22.9% | — |
Knowledge Claude Opus 4.6 leads
Claude Opus 4.6: 61.8 (#23), Grok 4.20 Multi-Agent: 39.7 (#116)
| Benchmark | Claude Opus 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Expert | 1546 | 1445 |
| GPQA Diamond | 90.5% | — |
| Humanity's Last Exam | 34.4% | — |
| SimpleQA Verified | 47% | — |
| Vectara Hallucination Rate | 12.2% | — |
Multimodal Grok 4.20 Multi-Agent leads
Claude Opus 4.6: 37.0 (#67), Grok 4.20 Multi-Agent: 39.8 (#44)
| Benchmark | Claude Opus 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Vision | 1316 | 1259 |
| Furniture Assembly | 28.3% | — |
| LMArena Document | 1507 | — |
Multilingual Claude Opus 4.6 leads
Claude Opus 4.6: 58.2 (#4), Grok 4.20 Multi-Agent: 54.6 (#40)
| Benchmark | Claude Opus 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Non-English | 1490 | 1440 |
| LMArena Chinese | 1551 | 1475 |
| LMArena French | 1513 | 1467 |
| LMArena German | 1504 | 1456 |
| LMArena Japanese | 1484 | 1405 |
| LMArena Korean | 1465 | 1416 |
| LMArena Russian | 1497 | 1457 |
| LMArena Spanish | 1512 | 1447 |
Instruction Following Claude Opus 4.6 leads
Claude Opus 4.6: 79.7 (#3), Grok 4.20 Multi-Agent: 75.0 (#80)
| Benchmark | Claude Opus 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Instruction Following | 1523 | 1420 |
Long Context Claude Opus 4.6 leads
Claude Opus 4.6: 48.1 (#13), Grok 4.20 Multi-Agent: 43.7 (#84)
| Benchmark | Claude Opus 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Longer Query | 1520 | 1430 |
| CL-bench | 20.7% | — |
| CL-bench Life | 17% | — |
Writing & Preference Claude Opus 4.6 leads
Claude Opus 4.6: 73.7 (#9), Grok 4.20 Multi-Agent: 64.1 (#57)
| Benchmark | Claude Opus 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Text | 1504 | 1450 |
| LMArena Creative Writing | 1506 | 1435 |
| LMArena Multi-Turn | 1514 | 1451 |
| EQ-Bench Creative Writing | 1809 | — |
| EQ-Bench 4 | 1223 | — |
Frequently asked questions
Is Claude Opus 4.6 better than Grok 4.20 Multi-Agent?
Claude Opus 4.6 is the stronger model overall, scoring 58.3 to 45.5 on the Noometry Index. Grok 4.20 Multi-Agent costs 6.4× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4.6 or Grok 4.20 Multi-Agent?
Grok 4.20 Multi-Agent is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; Claude Opus 4.6 lists at $5 and $25.
Is Claude Opus 4.6 or Grok 4.20 Multi-Agent better for coding?
Claude Opus 4.6 scores higher on coding benchmarks: 57.7 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Opus 4.6 and Grok 4.20 Multi-Agent share?
20 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and Grok 4.20 Multi-Agent has 20.