Across 12 comparable benchmarks, Claude Sonnet 4.5 has better reported results on 12 and worse on 0.
Strong evidence12 of 12 shared results countedHow we compare
Price basis: Listed rates vs standard rates. The price section below shows the applicable periods.
| Fact | Qwen3-30B-A3B-2507 | Claude Sonnet 4.5 |
|---|---|---|
| Context window | 256K tokens | 1M tokens |
| Input / 1M | — | $3.00 |
| Output / 1M | — | $15.00 |
| Blended (4:1) | — | $3.46 |
| Status | Deprecated | Deprecated |
| Released | July 29, 2025 | September 30, 2025 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 7 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Claude Sonnet 4.5 ahead on 2 of 2 counted
Claude Sonnet 4.5 ahead on 1 of 1 counted
Claude Sonnet 4.5 ahead on 3 of 3 counted
Claude Sonnet 4.5 ahead on 1 of 1 counted
Claude Sonnet 4.5 ahead on 1 of 1 counted
Claude Sonnet 4.5 ahead on 2 of 2 counted
No shared comparable results for Abstract reasoning, Computer & tool use, Long context, Cybersecurity.
Published scores, with matching modes where available. Gaps show Qwen3-30B-A3B-2507 relative to Claude Sonnet 4.5. Reading the results
| Benchmark | Qwen3-30B-A3B-2507 | Claude Sonnet 4.5 | Gap |
|---|---|---|---|
| SWE-bench VerifiedRepository Engineering · Accuracy | 22.0Thinking · no tools | 82.0≠Parallel Thinking · tools | −60.0 pts#107 vs #8 of 108 |
| Terminal Bench HardAgentic Development · Accuracy | 5.3Thinking · tools | 35.6Thinking · tools | −30.3 pts#135 vs #47 of 157 |
| AIME2025Mathematics · Accuracy | 61.3Normal · no tools | 100.0≠Thinking · tools | −38.7 pts#75 vs #1 of 86 |
| CritPtScientific Reasoning · Score | 0.3Thinking · no tools | 1.1Thinking · no tools | 0.27×#124 vs #103 of 134 |
| GPQA DiamondScientific Reasoning · Accuracy | 70.4Normal · no tools | 73.7Normal · no tools | −3.3 pts#138 vs #124 of 200 |
| SciCodeScientific Computing · Score | 33.0Thinking · no tools | 45.7Thinking · no tools | 0.72×#89 vs #61 of 98 |
| BrowseCompFact Finding · Accuracy | 2.3Thinking · tools | 24.1Thinking · tools | −21.8 pts#61 vs #59 of 61 |
| GDP.pdfDocuments & Charts · Task pass rate (%) | 0.4Thinking · no tools | 5.2Thinking · no tools | −4.8 pts#96 vs #74 of 96 |
| τ²-BenchService Workflows · Accuracy | 49.0Thinking · tools | 84.7Thinking · tools | −35.7 pts#33 vs #9 of 40 |
| τ³-BankingService Workflows · Score | 5.4Thinking · tools | 24.5Thinking · tools | 0.22×#107 vs #49 of 120 |
| HLEKnowledge Exams · Accuracy | 9.8Thinking · no tools | 33.6≠Thinking · tools | −23.8 pts#128 vs #84 of 151 |
| MMLU-ProKnowledge Exams · Accuracy | 78.4Normal · no tools | 88.0≠Thinking · no tools | −9.6 pts#69 vs #7 of 153 |
Repository Engineering · Accuracy
Agentic Development · Accuracy
Mathematics · Accuracy
Scientific Reasoning · Score
Scientific Reasoning · Accuracy
Scientific Computing · Score
Fact Finding · Accuracy
Documents & Charts · Task pass rate (%)
Service Workflows · Accuracy
Service Workflows · Score
A dash means no result is available.
| Benchmark | Qwen3-30B-A3B-2507 | Claude Sonnet 4.5 |
|---|---|---|
| FrontierMath | — | 5.2 |
| FrontierMath - Tier 4 | — | 4.2 |
| FrontierMath Tier 4 v2 | — | 2.4 |
| FrontierMath v2 | — | 23.9 |
| APEX-SWE | — | 31.0 |
| CodeClash | — | 1389 |
| GSO | — | 14.7 |
| LiveCodeBench | 43.2 | — |
| SWE-Bench Pro - Public | — | 43.6 |
| Terminal Bench 2.0 | — | 42.8 |
| Terminal-Bench 1.0 | — | 50.0 |
| Vibe Code Bench v1.1 | — | 22.6 |
| WeirdML v2 | — | 47.7 |
| Claw Bench | — | 88.1 |
| MCP-Atlas | — | 59.5 |
| OSWorld-Verified | — | 62.9 |
| Pinch Bench | — | 88.2 |
| ECI | — | 147 |
| LiveBench | — | 68.2 |
| METR Time Horizons v1.1 | — | 122 |
| Text Arena (Coding) | — | 1391 |
| Creative Writing | — | 1677 |
| IF Bench | — | 57.3 |
| EBR-bench | — | 2.4 |
| GeoBench ACW | — | 60.0 |
| MMMU | — | 77.8 |
| MMMU-Pro | — | 68.9 |
| VPCT | — | 39.8 |
| GDPval-AA | — | 39.0 |
| SAGE | — | 36.1 |
| τ²-Bench - Telecom | — | 98.0 |
| ARC-AGI-1 | — | 63.7 |
| ARC-AGI-2 | — | 13.6 |
| SimpleBench | — | 54.3 |
| Vending-Bench 2 | — | 3839 |
| GAIA | — | 74.5 |
| MedCode | — | 44.1 |
| MedScribe | — | 84.5 |
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.
Qwen3-30B-A3B-2507: Listed text rates; pricing tier not confirmed.
Claude Sonnet 4.5: Standard pricing. Anthropic official pricing (platform.claude.com/docs/en/about-claude/pricing) verified 2026-11-13; Deprecated 2026-09-30; tentative retirement 2026-11-30 (replacement: claude-sonnet-5-5)
| Price / 1M tokens | Qwen3-30B-A3B-2507 | Claude Sonnet 4.5 | Ratio |
|---|---|---|---|
| Input | — | $3.00 | — |
| Output | — | $15.00 | — |
| Cached input | — | $0.30 | — |
| Cache write | — | — | — |
| Blended | — | $3.46 | — |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
| Attribute | Qwen3-30B-A3B-2507 | Claude Sonnet 4.5 |
|---|---|---|
| Availability | Deprecated | Deprecated |
| Provider | Alibaba | Anthropic |
| Model type | Chat model | Chat model |
| First release | July 29, 2025 | September 30, 2025 |
| Context window | 256K tokens | 1M tokens |
| Max output | 16K tokens | 64K tokens |
| Total parameters | 30.5B | — |
| Active parameters | 3.3B | — |
| Architecture | Mixture of Experts (MoE) | Undisclosed |
| Documented capabilities | 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 Qwen3-30B-A3B-2507 or Claude Sonnet 4.5? 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.