Across 3 comparable benchmarks, Claude Sonnet 4 has better reported results on 2 and worse on 1.
Moderate evidence3 of 3 shared results countedHow we compare
Claude Sonnet 4 is no longer available through its official API. API prices for this version are not shown.
Price basis: Listed rates vs listed rates. The price section below shows the applicable periods.
| Fact | QwQ-32B-Preview | Claude Sonnet 4 |
|---|---|---|
| Context window | 32K tokens | 200K tokens |
| Input / 1M | — | — |
| Output / 1M | — | — |
| Blended (4:1) | — | — |
| Status | Available | Retired |
| Released | November 28, 2024 | May 23, 2025 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 2 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Split 1–1 of 2 counted
No shared comparable results for Coding, Abstract reasoning, Science & health, Computer & tool use, Research & search, Long context, Multimodal, Professional work & productivity, Cybersecurity.
Published scores, with matching modes where available. Gaps show QwQ-32B-Preview relative to Claude Sonnet 4. Reading the results
| Benchmark | QwQ-32B-Preview | Claude Sonnet 4 | Gap |
|---|---|---|---|
| AIME 2024Mathematics · Accuracy | 50.0Normal · no tools | 43.4Normal · no tools | +6.6 pts#41 vs #45 of 54 |
| MATH-500Mathematics · Accuracy | 90.6Normal · no tools | 99.1≠Thinking · no tools | −8.5 pts#43 vs #4 of 49 |
| MMLU-ProKnowledge Exams · Accuracy | 71.0Normal · no tools | 84.0≠Thinking · no tools | −13.0 pts#90 vs #42 of 153 |
Knowledge Exams · Accuracy
A dash means no result is available.
| Benchmark | QwQ-32B-Preview | Claude Sonnet 4 |
|---|---|---|
| AIME2025 | — | 85.0 |
| CritPt | — | 1.1 |
| FrontierMath | — | 4.1 |
| FrontierMath - Tier 4 | — | 0.0 |
| GPQA Diamond | — | 83.8 |
| HLE | — | 9.6 |
| IMO-ProofBench | — | 27.1 |
| IMO-ProofBench Advanced | — | 4.8 |
| Aider-Polyglot | — | 61.3 |
| CodeClash | — | 1223 |
| IOI 2024 (Vals v1) | — | 9.7 |
| IOI 2025 (Vals v1) | — | 4 |
| LiveCodeBench | — | 48.5 |
| SWE-Bench Pro - Commercial | — | 9.1 |
| SWE-Bench Pro - Public | — | 42.7 |
| SWE-bench Verified | — | 80.2 |
| Terminal Bench Hard | — | 31.1 |
| Terminal-Bench 1.0 | — | 41.3 |
| Claw Bench | — | 77.8 |
| OSWorld-Verified | — | 42.2 |
| Pinch Bench | — | 80.5 |
| PinchBench v2 | — | 48.8 |
| ECI | — | 142 |
| LiveBench | — | 61.3 |
| Creative Writing | — | 1483 |
| IF Bench | — | 55.0 |
| Fiction.liveBench | — | 46.9 |
| MMMU | — | 74.4 |
| MMMU-Pro | — | 62.4 |
| VPCT | — | 34.0 |
| GDPval-AA | — | 33.0 |
| SAGE | — | 35.0 |
| τ²-Bench | — | 52.0 |
| τ³-Banking | — | 16.7 |
| ARC-AGI-1 | — | 40.0 |
| ARC-AGI-2 | — | 5.9 |
| SimpleBench | — | 45.5 |
| MedCode | — | 35.0 |
| MedScribe | — | 72.4 |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
A blended cost needs a published input and output price on both sides, and one of these two does not have them yet.
QwQ-32B-Preview: Listed text rates; pricing tier not confirmed.
Claude Sonnet 4: Listed text rates; pricing tier not confirmed.
| Price / 1M tokens | QwQ-32B-Preview | Claude Sonnet 4 | Ratio |
|---|---|---|---|
| Input | — | — | — |
| Output | — | — | — |
| Cached input | — | — | — |
| Cache write | — | — | — |
| Blended | — | — | — |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Lower prices are highlighted. The cache hit rate applies to input tokens only; models without a published cached-input rate use their normal input price for those tokens.Effective dates: QwQ-32B-Preview —; Claude Sonnet 4 2026-11-14.Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
| Attribute | QwQ-32B-Preview | Claude Sonnet 4 |
|---|---|---|
| Availability | Available | Retired |
| Provider | Alibaba | Anthropic |
| Model type | Reasoning model | Reasoning model |
| First release | November 28, 2024 | May 23, 2025 |
| Context window | 32K tokens | 200K tokens |
| Max output | — | 64K tokens |
| Total parameters | 32B | — |
| Architecture | Dense | Undisclosed |
| Documented capabilities | Reasoning, Multilingual | Reasoning, Multilingual |
| Input modalities | Text | Text, Image |
| Output modalities | Text | Text |
| Weights | Open weights | Closed / API only |
| Licence | Apache 2.0 | — |
| Commercial use | Commercial use allowed | Proprietary |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used QwQ-32B-Preview or Claude Sonnet 4? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.