Model comparison
Claude 2 vs Claude Opus 5.5
Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 25.0 on the Noometry Index.
Last verified . 4 shared benchmarks.
Summary
- They share 4 benchmarks with published results for both. Claude 2 scores higher in 0 categories and Claude Opus 5.5 in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 5.5 leads 91.8 to 9.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 2 and 100% for Claude Opus 5.5.
Side by side
| Claude 2 | Claude Opus 5.5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 25.0 | 68.6 |
| Released | 2023-07-11 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 128K |
| Input $ / M tokens | — | $4 |
| Output $ / M tokens | — | $20 |
| Results tracked | 8 | 44 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude 2: —, Claude Opus 5.5: 71.9 (#3)
| Benchmark | Claude 2 | Claude Opus 5.5 |
|---|---|---|
| FrontierCode | — | 54.6% |
| CursorBench | — | 57.8% |
| LMArena WebDev | — | 1813 |
| FrontierSWE | — | 62.3% |
| SciCode | — | 66.9% |
| LMArena Coding | — | 1547 |
| MirrorCode | — | 77.4% |
| ALE-Bench | — | 2,147 |
| HumanEval+ | 61.6% | — |
Agentic & Tool Use Not comparable
Claude 2: —, Claude Opus 5.5: 45.3 (#15)
| Benchmark | Claude 2 | Claude Opus 5.5 |
|---|---|---|
| APEX-Agents | — | 73.5% |
| GDP.pdf | — | 30.6% |
| Vending-Bench 2 | — | 9,235 |
Reasoning Claude Opus 5.5 leads
Claude 2: 21.7 (#216), Claude Opus 5.5: 80.2 (#3)
| Benchmark | Claude 2 | Claude Opus 5.5 |
|---|---|---|
| DTBench | 51.9% | 98.9% |
| Epoch Capabilities Index | 120.13 | 167.33 |
| ARC-AGI-2 | — | 93.3% |
| NYT Connections (extended) | — | 88.5% |
| ARC-AGI-1 | — | 98.5% |
| CritPt | — | 31.7% |
| EBR-Bench | — | 71.4% |
| LMArena Hard Prompts | — | 1535 |
| Mystery Game Puzzles | — | 71% |
| LMCA | — | 68.2% |
Math Claude Opus 5.5 leads
Claude 2: 9.3 (#320), Claude Opus 5.5: 91.8 (#3)
| Benchmark | Claude 2 | Claude Opus 5.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 100% |
| FrontierMath (Tiers 1-3) | — | 91.2% |
| FrontierMath Tier 4 | — | 95% |
| ProofBench | — | 100% |
| LMArena Math | — | 1506 |
| MATH Level 5 | 11.7% | — |
| FrontierMath Erdős | — | 2.9% |
Knowledge Claude Opus 5.5 leads
Claude 2: 16.9 (#287), Claude Opus 5.5: 66.4 (#10)
| Benchmark | Claude 2 | Claude Opus 5.5 |
|---|---|---|
| GPQA Diamond | 34.7% | 90.6% |
| SimpleQA Verified | — | 72.2% |
| LMArena Expert | — | 1547 |
| MMLU | 78.5% | — |
| TriviaQA | 87.5% | — |
Multimodal Not comparable
Claude 2: —, Claude Opus 5.5: 57.8 (#1)
| Benchmark | Claude 2 | Claude Opus 5.5 |
|---|---|---|
| LMArena Vision | — | 1321 |
| Blueprint-Bench 2 | — | 51.2% |
| Furniture Assembly | — | 83.3% |
Multilingual Not comparable
Claude 2: —, Claude Opus 5.5: 59.1 (#2)
| Benchmark | Claude 2 | Claude Opus 5.5 |
|---|---|---|
| LMArena Non-English | — | 1507 |
| LMArena Chinese | — | 1588 |
| LMArena French | — | 1514 |
| LMArena Russian | — | 1520 |
| LMArena Spanish | — | 1507 |
Instruction Following Not comparable
Claude 2: —, Claude Opus 5.5: 80.0 (#3)
| Benchmark | Claude 2 | Claude Opus 5.5 |
|---|---|---|
| LMArena Instruction Following | — | 1537 |
Long Context Not comparable
Claude 2: —, Claude Opus 5.5: 47.1 (#19)
| Benchmark | Claude 2 | Claude Opus 5.5 |
|---|---|---|
| LMArena Longer Query | — | 1532 |
Writing & Preference Not comparable
Claude 2: —, Claude Opus 5.5: 78.2 (#3)
| Benchmark | Claude 2 | Claude Opus 5.5 |
|---|---|---|
| LMArena Text | — | 1515 |
| LMArena Creative Writing | — | 1533 |
| EQ-Bench Creative Writing | — | 2050 |
| LMArena Multi-Turn | — | 1499 |
Frequently asked questions
Is Claude 2 better than Claude Opus 5.5?
Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 25.0 on the Noometry Index.
How many benchmarks do Claude 2 and Claude Opus 5.5 share?
4 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and Claude Opus 5.5 has 44.