# Claude Sonnet 4.5 vs Qwen2.5 72B Instruct

> Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 31.9 on the Noometry Index. Qwen2.5 72B Instruct costs 2.4× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-5-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-12
- Shared benchmarks: 31

## Summary

- They share 31 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 9 categories and Qwen2.5 72B Instruct in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Sonnet 4.5 leads 48.4 to 27.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Claude Sonnet 4.5 and 8.1% for Qwen2.5 72B Instruct.
- Qwen2.5 72B Instruct is cheaper at $1.40 / $5.60 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
- Claude Sonnet 4.5 accepts more context: 200K tokens versus 131K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 4.5 | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 44.1 | 31.9 |
| Rank | 81 | 267 |
| Context | 200K | 131K |
| Input $/M | $3 | $1.40 |
| Output $/M | $15 | $5.60 |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 4.5: 47.3 (#61)
- Qwen2.5 72B Instruct: 33.2 (#260)

| Benchmark | Claude Sonnet 4.5 | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | 47.7% | 16% |
| LMArena Coding | 1489 | 1292 |
| SWE-bench Verified | 71.3% | — |
| SWE-bench Verified (bash only) | 71.4% | — |
| LMArena WebDev | 1393 | — |
| SWE-bench Multilingual | 67% | — |
| SciCode | 44.7% | — |
| GSO | 14.7% | — |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
| ALE-Bench | 796.15 | — |
| AlgoTune | 1.52 | — |

## Agentic & Tool Use

- Claude Sonnet 4.5: 38.3 (#32)
- Qwen2.5 72B Instruct: 22.1 (#133)

| Benchmark | Claude Sonnet 4.5 | Qwen2.5 72B Instruct |
|---|---|---|
| METR Time Horizons | 67.4% | 35.8% |
| Terminal-Bench | 46.5% | — |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| TheAgentCompany | — | 5.7% |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| BALROG | — | 16.2% |
| LMArena Search | 1159 | — |
| Vending-Bench 2 | 3,839 | — |

## Reasoning

- Claude Sonnet 4.5: 26.9 (#125)
- Qwen2.5 72B Instruct: 22.3 (#199)

| Benchmark | Claude Sonnet 4.5 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1462 | 1271 |
| DTBench | 83.2% | 62.9% |
| LMCA | 38.8% | 13.4% |
| Epoch Capabilities Index | 146.84 | 129 |
| ForecastBench | 61.9 | 57.5 |
| ARC-AGI-2 | 13.6% | — |
| SimpleBench | 54.3% | — |
| Kagi LLM Benchmark | 57.9% | — |
| NYT Connections (extended) | 37.3% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 17% | — |
| BIG-Bench Hard | — | 79.8% |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |

## Math

- Claude Sonnet 4.5: 32.3 (#216)
- Qwen2.5 72B Instruct: 19.3 (#287)

| Benchmark | Claude Sonnet 4.5 | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 8.1% |
| Omni-MATH | 55.3% | 33% |
| LMArena Math | 1449 | 1283 |
| MATH Level 5 | 97.7% | 63.2% |
| FrontierMath (Tiers 1-3) | 23.9% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 19% | — |
| FrontierMath (Feb 2025 set) | 15.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Claude Sonnet 4.5: 48.4 (#76)
- Qwen2.5 72B Instruct: 27.0 (#253)

| Benchmark | Claude Sonnet 4.5 | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 82.3% | 49.1% |
| MMLU-Pro | 86.9% | 63.1% |
| GPQA (HELM) | 68.6% | 42.6% |
| LMArena Expert | 1482 | 1245 |
| Humanity's Last Exam | 13.7% | — |
| SimpleQA Verified | 30.7% | — |
| Confabulations | — | 19.1% |
| Vectara Hallucination Rate | 12% | — |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |

## Multimodal

- Claude Sonnet 4.5: 34.8 (#89)
- Qwen2.5 72B Instruct: —

| Benchmark | Claude Sonnet 4.5 | Qwen2.5 72B Instruct |
|---|---|---|
| VPCT | 39.8% | — |
| LMArena Document | 1450 | — |

## Multilingual

- Claude Sonnet 4.5: 53.4 (#69)
- Qwen2.5 72B Instruct: 41.0 (#213)

| Benchmark | Claude Sonnet 4.5 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1425 | 1252 |
| LMArena Chinese | 1459 | 1272 |
| LMArena French | 1458 | 1280 |
| LMArena German | 1427 | 1234 |
| LMArena Japanese | 1390 | 1180 |
| LMArena Korean | 1403 | 1188 |
| LMArena Russian | 1437 | 1264 |
| LMArena Spanish | 1457 | 1256 |

## Instruction Following

- Claude Sonnet 4.5: 75.0 (#78)
- Qwen2.5 72B Instruct: 65.5 (#221)

| Benchmark | Claude Sonnet 4.5 | Qwen2.5 72B Instruct |
|---|---|---|
| IFEval | 85% | 80.6% |
| LMArena Instruction Following | 1459 | 1254 |

## Long Context

- Claude Sonnet 4.5: 45.2 (#46)
- Qwen2.5 72B Instruct: 38.9 (#188)

| Benchmark | Claude Sonnet 4.5 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1476 | 1282 |

## Writing & Preference

- Claude Sonnet 4.5: 66.5 (#34)
- Qwen2.5 72B Instruct: 46.7 (#215)

| Benchmark | Claude Sonnet 4.5 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1439 | 1269 |
| LMArena Creative Writing | 1442 | 1221 |
| WildBench | 85.4% | 80.2% |
| LMArena Multi-Turn | 1465 | 1272 |
| EQ-Bench Creative Writing | 1678 | — |

## FAQ

### Is Claude Sonnet 4.5 better than Qwen2.5 72B Instruct?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 31.9 on the Noometry Index. Qwen2.5 72B Instruct costs 2.4× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 4.5 or Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct is cheaper. It lists at $1.40 per million input tokens and $5.60 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

### Is Claude Sonnet 4.5 or Qwen2.5 72B Instruct better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 33.2 in the Noometry coding category.

### Which has the bigger context window?

Claude Sonnet 4.5 does, with 200K tokens against 131K.

### How many benchmarks do Claude Sonnet 4.5 and Qwen2.5 72B Instruct share?

31 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Qwen2.5 72B Instruct has 43.