# Claude Opus 5 vs Qwen1.5-72B

> Claude Opus 5 is the stronger model overall, scoring 67.8 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-opus-5-vs-qwen1-5-72b
- Last updated: 2026-10-12
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Claude Opus 5 scores higher in 8 categories and Qwen1.5-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Opus 5 leads 66.8 to 11.5.
- The biggest single-benchmark swing is GPQA Diamond: 93.9% for Claude Opus 5 and 28.8% for Qwen1.5-72B.
- Qwen1.5-72B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Opus 5 | Qwen1.5-72B |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 67.8 | 30.8 |
| Rank | 4 | 285 |
| Context | 1M | — |
| Input $/M | $5 | — |
| Output $/M | $25 | — |
| Weights | Proprietary | Open |

## Coding

- Claude Opus 5: 67.5 (#5)
- Qwen1.5-72B: 31.9 (#277)

| Benchmark | Claude Opus 5 | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1534 | 1165 |
| DeepSWE | 73.6% | — |
| FrontierCode | 53.4% | — |
| CursorBench | 46.6% | — |
| LMArena WebDev | 1691 | — |
| FrontierSWE | 52% | — |
| SciCode | 56.4% | — |
| WeirdML | 91.8% | — |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| ALE-Bench | 2,165 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |

## Agentic & Tool Use

- Claude Opus 5: 55.6 (#1)
- Qwen1.5-72B: —

| Benchmark | Claude Opus 5 | Qwen1.5-72B |
|---|---|---|
| APEX-Agents | 65.8% | — |
| OSWorld 2.0 | 31.4% | — |
| τ²-bench Banking | 48.7% | — |
| PostTrainBench | 35% | — |
| BALROG | 63.4% | — |
| GBAEval | 79.6% | — |
| GDP.pdf | 24% | — |
| Vending-Bench 2 | 11,182 | — |

## Reasoning

- Claude Opus 5: 77.2 (#4)
- Qwen1.5-72B: 22.2 (#203)

| Benchmark | Claude Opus 5 | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1526 | 1148 |
| ARC-AGI-2 | 90.4% | — |
| SimpleBench | 80.6% | — |
| NYT Connections (extended) | 94.3% | — |
| ARC-AGI-1 | 97.5% | — |
| CritPt | 29.1% | — |
| Chess Puzzles | 42% | — |
| EBR-Bench | 45.7% | — |
| Mystery Game Puzzles | 59% | — |
| DTBench | 97.9% | — |
| LMCA | 64.5% | — |
| Bench to the Future 3 | 0.12 | — |
| Epoch Capabilities Index | 162.78 | — |

## Math

- Claude Opus 5: 86.2 (#8)
- Qwen1.5-72B: 33.2 (#205)

| Benchmark | Claude Opus 5 | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1531 | 1164 |
| FrontierMath (Tiers 1-3) | 85.6% | — |
| FrontierMath Tier 4 | 73.2% | — |
| OTIS Mock AIME 2024-2025 | 98.9% | — |
| ProofBench | 99% | — |

## Knowledge

- Claude Opus 5: 66.8 (#9)
- Qwen1.5-72B: 11.5 (#300)

| Benchmark | Claude Opus 5 | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | 93.9% | 28.8% |
| LMArena Expert | 1557 | 1136 |
| SimpleQA Verified | 59.9% | — |

## Multimodal

- Claude Opus 5: 50.8 (#8)
- Qwen1.5-72B: —

| Benchmark | Claude Opus 5 | Qwen1.5-72B |
|---|---|---|
| LMArena Vision | 1319 | — |
| Blueprint-Bench 2 | 30.4% | — |
| Furniture Assembly | 60.8% | — |
| LMArena Document | 1516 | — |

## Multilingual

- Claude Opus 5: 58.8 (#4)
- Qwen1.5-72B: 33.2 (#253)

| Benchmark | Claude Opus 5 | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1501 | 1135 |
| LMArena Chinese | 1574 | 1186 |
| LMArena French | 1519 | 1159 |
| LMArena German | 1524 | 1084 |
| LMArena Japanese | 1516 | 1061 |
| LMArena Korean | 1521 | 1050 |
| LMArena Russian | 1507 | 1104 |
| LMArena Spanish | 1519 | 1110 |

## Instruction Following

- Claude Opus 5: 79.2 (#7)
- Qwen1.5-72B: 59.3 (#256)

| Benchmark | Claude Opus 5 | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1517 | 1141 |

## Long Context

- Claude Opus 5: 46.5 (#21)
- Qwen1.5-72B: 35.1 (#243)

| Benchmark | Claude Opus 5 | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1515 | 1157 |

## Writing & Preference

- Claude Opus 5: 79.2 (#1)
- Qwen1.5-72B: 37.3 (#258)

| Benchmark | Claude Opus 5 | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1507 | 1166 |
| LMArena Creative Writing | 1491 | 1137 |
| LMArena Multi-Turn | 1499 | 1160 |
| EQ-Bench Creative Writing | 2133 | — |
| EQ-Bench 4 | 1385 | — |

## FAQ

### Is Claude Opus 5 better than Qwen1.5-72B?

Claude Opus 5 is the stronger model overall, scoring 67.8 to 30.8 on the Noometry Index.

### Is Claude Opus 5 or Qwen1.5-72B better for coding?

Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 31.9 in the Noometry coding category.

### How many benchmarks do Claude Opus 5 and Qwen1.5-72B share?

18 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and Qwen1.5-72B has 22.