Model comparison
Claude 3 Opus vs Claude Opus 4.6
Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 29.5 on the Noometry Index.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and Claude Opus 4.6 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4.6 leads 63.0 to 14.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 94.4% for Claude Opus 4.6.
Side by side
| Claude 3 Opus | Claude Opus 4.6 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 29.5 | 58.2 |
| Released | 2024-02-29 | 2026-02-04 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 128K |
| Input $ / M tokens | — | $5 |
| Output $ / M tokens | — | $25 |
| Results tracked | 46 | 68 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.6 leads
Claude 3 Opus: 32.9 (#267), Claude Opus 4.6: 57.2 (#20)
| Benchmark | Claude 3 Opus | Claude Opus 4.6 |
|---|---|---|
| WeirdML | 19.2% | 78% |
| LMArena Coding | 1264 | 1536 |
| SWE-bench Verified | — | 78.7% |
| FrontierCode | — | 26.6% |
| SWE-bench Verified (bash only) | — | 75.6% |
| LMArena WebDev | — | 1547 |
| SWE-bench Multilingual | — | 72% |
| GSO | — | 41.2% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 996.5 |
| AlgoTune | — | 1.47 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Claude Opus 4.6 leads
Claude 3 Opus: 24.6 (#116), Claude Opus 4.6: 51.1 (#4)
| Benchmark | Claude 3 Opus | Claude Opus 4.6 |
|---|---|---|
| Cybench | 10% | 93% |
| METR Time Horizons | 29.5% | 78.9% |
| Terminal-Bench | — | 79.8% |
| APEX-Agents | — | 46.3% |
| Remote Labor Index | — | 4.2% |
| τ²-bench Banking | — | 27.3% |
| DeepResearch Bench | — | 55.3% |
| GBAEval | — | 44.1% |
| LMArena Search | — | 1253 |
| Vending-Bench 2 | — | 8,018 |
Reasoning Claude Opus 4.6 leads
Claude 3 Opus: 14.6 (#324), Claude Opus 4.6: 57.8 (#23)
| Benchmark | Claude 3 Opus | Claude Opus 4.6 |
|---|---|---|
| SimpleBench | 23.5% | 67.6% |
| Chess Puzzles | 5% | 17% |
| EnigmaEval | 0.8% | 7.6% |
| LMArena Hard Prompts | 1245 | 1527 |
| DTBench | 61.6% | 91.2% |
| LMCA | 17% | 55.8% |
| Epoch Capabilities Index | 126.91 | 155.24 |
| ForecastBench | 58.4 | 60 |
| ARC-AGI-2 | — | 69.2% |
| Kagi LLM Benchmark | — | 83.6% |
| NYT Connections (extended) | — | 92.1% |
| ARC-AGI-1 | — | 94% |
| Thematic Generalization | — | 80.6% |
| EBR-Bench | — | 12.7% |
| LiveBench Reasoning | 40.6% | — |
| Mystery Game Puzzles | — | 25% |
| LiveBench Data Analysis | 57.9% | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Claude Opus 4.6 leads
Claude 3 Opus: 14.8 (#299), Claude Opus 4.6: 63.0 (#31)
| Benchmark | Claude 3 Opus | Claude Opus 4.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 94.4% |
| LMArena Math | 1273 | 1519 |
| FrontierMath (Tiers 1-3) | — | 66% |
| FrontierMath Tier 4 | — | 26.8% |
| MathArena Final-Answer Competitions | — | 78.5% |
| ProofBench | — | 50% |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
| FrontierMath (Feb 2025 set) | — | 40.7% |
| FrontierMath Tier 4 (v1) | — | 22.9% |
Knowledge Claude Opus 4.6 leads
Claude 3 Opus: 24.5 (#267), Claude Opus 4.6: 61.9 (#26)
| Benchmark | Claude 3 Opus | Claude Opus 4.6 |
|---|---|---|
| GPQA Diamond | 47.2% | 90.5% |
| SimpleQA Verified | 12.6% | 47% |
| LMArena Expert | 1223 | 1546 |
| Humanity's Last Exam | — | 34.4% |
| Confabulations | 22.7% | — |
| Vectara Hallucination Rate | — | 12.2% |
| MMLU | 84.6% | — |
Multimodal Claude Opus 4.6 leads
Claude 3 Opus: 27.1 (#116), Claude Opus 4.6: 37.3 (#74)
| Benchmark | Claude 3 Opus | Claude Opus 4.6 |
|---|---|---|
| LMArena Vision | 1023 | 1316 |
| Furniture Assembly | — | 28.3% |
| LMArena Document | — | 1507 |
Multilingual Claude Opus 4.6 leads
Claude 3 Opus: 41.4 (#207), Claude Opus 4.6: 57.9 (#6)
| Benchmark | Claude 3 Opus | Claude Opus 4.6 |
|---|---|---|
| LMArena Non-English | 1258 | 1489 |
| LMArena Chinese | 1248 | 1551 |
| LMArena French | 1275 | 1513 |
| LMArena German | 1258 | 1502 |
| LMArena Japanese | 1204 | 1484 |
| LMArena Korean | 1187 | 1464 |
| LMArena Russian | 1280 | 1497 |
| LMArena Spanish | 1246 | 1510 |
Instruction Following Claude Opus 4.6 leads
Claude 3 Opus: 64.1 (#228), Claude Opus 4.6: 79.5 (#4)
| Benchmark | Claude 3 Opus | Claude Opus 4.6 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1523 |
| LiveBench Instruction Following | 63.9% | — |
Long Context Claude Opus 4.6 leads
Claude 3 Opus: 38.2 (#202), Claude Opus 4.6: 48.1 (#13)
| Benchmark | Claude 3 Opus | Claude Opus 4.6 |
|---|---|---|
| LMArena Longer Query | 1259 | 1520 |
| CL-bench | — | 20.7% |
| CL-bench Life | — | 17% |
Writing & Preference Claude Opus 4.6 leads
Claude 3 Opus: 47.2 (#213), Claude Opus 4.6: 73.5 (#10)
| Benchmark | Claude 3 Opus | Claude Opus 4.6 |
|---|---|---|
| LMArena Text | 1262 | 1503 |
| LMArena Creative Writing | 1235 | 1505 |
| LMArena Multi-Turn | 1275 | 1513 |
| EQ-Bench Creative Writing | — | 1809 |
| EQ-Bench 4 | — | 1223 |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Claude Opus 4.6?
Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Claude Opus 4.6 better for coding?
Claude Opus 4.6 scores higher on coding benchmarks: 57.2 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Claude Opus 4.6 share?
31 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Claude Opus 4.6 has 68.