Model comparison
Claude Sonnet 4 vs Qwen2.5 7B Instruct
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 20× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Last verified . 10 shared benchmarks.
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. Claude Sonnet 4 scores higher in 7 categories and Qwen2.5 7B Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4 leads 43.3 to 12.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for Claude Sonnet 4 and 2.5% for Qwen2.5 7B Instruct.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- Claude Sonnet 4 accepts more context: 200K tokens versus 131K.
- Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 40.8 | 29.0 |
| Released | 2025-05-22 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 200K | 131K |
| Max output | 64K | 8K |
| Input $ / M tokens | $3 | $0.17 |
| Output $ / M tokens | $15 | $0.70 |
| Results tracked | 58 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 43.5 (#88), Qwen2.5 7B Instruct: 36.5 (#208)
| Benchmark | Claude Sonnet 4 | Qwen2.5 7B Instruct |
|---|---|---|
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1414 | — |
| BigCodeBench Complete | — | 46.1% |
| ALE-Bench | 655.35 | — |
Agentic & Tool Use Claude Sonnet 4 leads
Claude Sonnet 4: 38.5 (#31), Qwen2.5 7B Instruct: 23.8 (#124)
| Benchmark | Claude Sonnet 4 | Qwen2.5 7B Instruct |
|---|---|---|
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| BALROG | — | 7.8% |
| METR Time Horizons | 62% | — |
Reasoning Claude Sonnet 4 leads
Claude Sonnet 4: 22.9 (#187), Qwen2.5 7B Instruct: 14.8 (#322)
| Benchmark | Claude Sonnet 4 | Qwen2.5 7B Instruct |
|---|---|---|
| DTBench | 77.1% | 47.7% |
| LMCA | 29% | 6.4% |
| Epoch Capabilities Index | 141.69 | 118.51 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| ARC-AGI-1 | 40% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 0% |
| EnigmaEval | 3.1% | — |
| LMArena Hard Prompts | 1372 | — |
| ForecastBench | 60.2 | — |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), Qwen2.5 7B Instruct: 12.6 (#306)
| Benchmark | Claude Sonnet 4 | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 2.5% |
| Omni-MATH | 60.2% | 29.4% |
| LMArena Math | 1375 | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.8 (#108), Qwen2.5 7B Instruct: 17.0 (#286)
| Benchmark | Claude Sonnet 4 | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | 79.2% | 35.5% |
| MMLU-Pro | 84.3% | 53.9% |
| GPQA (HELM) | 70.6% | 34.1% |
| Humanity's Last Exam | 7.8% | — |
| Confabulations | 13.2% | — |
| Vectara Hallucination Rate | 10.3% | — |
| LMArena Expert | 1372 | — |
| MMLU | — | 72.9% |
Multimodal Not comparable
Claude Sonnet 4: 26.2 (#121), Qwen2.5 7B Instruct: —
| Benchmark | Claude Sonnet 4 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Not comparable
Claude Sonnet 4: 46.7 (#156), Qwen2.5 7B Instruct: —
| Benchmark | Claude Sonnet 4 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1333 | — |
| LMArena Chinese | 1350 | — |
| LMArena French | 1363 | — |
| LMArena German | 1331 | — |
| LMArena Japanese | 1302 | — |
| LMArena Korean | 1291 | — |
| LMArena Russian | 1355 | — |
| LMArena Spanish | 1357 | — |
Instruction Following Claude Sonnet 4 leads
Claude Sonnet 4: 71.7 (#145), Qwen2.5 7B Instruct: 63.2 (#231)
| Benchmark | Claude Sonnet 4 | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | 84% | 74.1% |
| LMArena Instruction Following | 1376 | — |
Long Context Not comparable
Claude Sonnet 4: 33.7 (#259), Qwen2.5 7B Instruct: —
| Benchmark | Claude Sonnet 4 | Qwen2.5 7B Instruct |
|---|---|---|
| Fiction.LiveBench | 46.9% | — |
| LMArena Longer Query | 1398 | — |
Writing & Preference Claude Sonnet 4 leads
Claude Sonnet 4: 57.1 (#132), Qwen2.5 7B Instruct: 48.8 (#195)
| Benchmark | Claude Sonnet 4 | Qwen2.5 7B Instruct |
|---|---|---|
| WildBench | 83.8% | 73.1% |
| LMArena Text | 1351 | — |
| LMArena Creative Writing | 1345 | — |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
| LMArena Multi-Turn | 1376 | — |
Frequently asked questions
Is Claude Sonnet 4 better than Qwen2.5 7B Instruct?
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 20× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 4 or Qwen2.5 7B Instruct?
Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or Qwen2.5 7B Instruct better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 4 does, with 200K tokens against 131K.
How many benchmarks do Claude Sonnet 4 and Qwen2.5 7B Instruct share?
10 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Qwen2.5 7B Instruct has 15.